Harmony_Parler_TTS_Large

import torch
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf

device = "cuda" if torch.cuda.is_available() else "cpu"

model_id = "SeifElden2342532/Harmony_Parler_TTS_Large"
model = ParlerTTSForConditionalGeneration.from_pretrained(model_id).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_id)

description = "A calm male voice with medium speed and clear audio"
prompt_text = "This is the text I want the model to say."

input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device)
prompt_input_ids = tokenizer(prompt_text, return_tensors="pt").input_ids.to(device)

generated = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
audio = generated.cpu().numpy().squeeze()

sf.write("out.wav", audio, model.config.sampling_rate)