facebook
/

wav2vec2-base-960h

Automatic Speech Recognition Transformers PyTorch TensorFlow Safetensors

English wav2vec2 audio hf-asr-leaderboard Eval Results Inference Endpoints

Model card Files Files and versions Community

patrickvonplaten commited on Feb 9, 2021

Commit

d79204c

•

1 Parent(s): 06c667b

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -32,14 +32,14 @@ The original model can be found under https://github.com/pytorch/fairseq/tree/ma
 To transcribe audio files the model can be used as a standalone acoustic model as follows:
 ```python
- from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForMaskedLM
  from datasets import load_dataset
  import soundfile as sf
  import torch
  # load model and tokenizer
  tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
- model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-base-960h")
  # define function to read in sound file
  def map_to_array(batch):
@@ -68,7 +68,7 @@ To transcribe audio files the model can be used as a standalone acoustic model a
 ```python
 from datasets import load_dataset
-from transformers import Wav2Vec2ForMaskedLM, Wav2Vec2Tokenizer
 import soundfile as sf
 import torch
 from jiwer import wer
@@ -76,7 +76,7 @@ from jiwer import wer
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
-model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
 tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
 def map_to_array(batch):

 To transcribe audio files the model can be used as a standalone acoustic model as follows:
 ```python
+ from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
  from datasets import load_dataset
  import soundfile as sf
  import torch
  # load model and tokenizer
  tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+ model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
  # define function to read in sound file
  def map_to_array(batch):
 ```python
 from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Tokenizer
 import soundfile as sf
 import torch
 from jiwer import wer
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
+model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
 tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
 def map_to_array(batch):