wav2vec2-large-robust-ft-libri-960h

136.4K
15
302M
1 language
license:apache-2.0
by
facebook
Audio Model
OTHER
Good
136K downloads
Production-ready
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
1GB+ RAM
Mobile
Laptop
Server
Quick Summary

This model is a fine-tuned version of the wav2vec2-large-robust model.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
1GB+ RAM

Code Examples

Usagepythontransformers
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import soundfile as sf
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 
 # define function to read in sound file
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])
     batch["speech"] = speech
     return batch
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 ds = ds.map(map_to_array)
 
 # tokenize
 input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)
Usagepythontransformers
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import soundfile as sf
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 
 # define function to read in sound file
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])
     batch["speech"] = speech
     return batch
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 ds = ds.map(map_to_array)
 
 # tokenize
 input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)
Usagepythontransformers
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import soundfile as sf
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 
 # define function to read in sound file
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])
     batch["speech"] = speech
     return batch
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 ds = ds.map(map_to_array)
 
 # tokenize
 input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)
Usagepythontransformers
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import soundfile as sf
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 
 # define function to read in sound file
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])
     batch["speech"] = speech
     return batch
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 ds = ds.map(map_to_array)
 
 # tokenize
 input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)
Usagepythontransformers
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import soundfile as sf
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 
 # define function to read in sound file
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])
     batch["speech"] = speech
     return batch
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 ds = ds.map(map_to_array)
 
 # tokenize
 input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)
Usagepythontransformers
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import soundfile as sf
 import torch
 
 # load model and processor
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-robust-ft-libri-960h")
 
 # define function to read in sound file
 def map_to_array(batch):
     speech, _ = sf.read(batch["file"])
     batch["speech"] = speech
     return batch
     
 # load dummy dataset and read soundfiles
 ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 ds = ds.map(map_to_array)
 
 # tokenize
 input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.