nemo-nano-codec-22khz-0.6kbps-12.5fps

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)

import librosa
import torch
import soundfile as sf
from nemo.collections.tts.models import AudioCodecModel

path_to_input_audio = ??? # path of the input audio
path_to_output_audio = ??? # path of the reconstructed output audio

# load audio codec model
nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps").eval()

# get discrete tokens from audio
audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)

device = 'cuda' if torch.cuda.is_available() else 'cpu'
audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)

encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)

# Reconstruct audio from tokens
reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)

# save reconstructed audio
output_audio = reconstructed_audio.cpu().numpy().squeeze()
sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)