Hugging Face's logo

Nhut
/
wav2vec2-large-xlsr-french

Automatic Speech Recognition
Transformers
PyTorch
JAX
French
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results
Inference Endpoints
Model card Files Community
1
Nhut commited on
Commit
ddf4550
•
1 Parent(s): 7eb8f5d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -79,8 +79,8 @@ import re
79
 
80
  test_dataset = load_dataset("common_voice", "fr")
81
  wer = load_metric("wer")
82
- processor = Wav2Vec2Processor.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-French")
83
- model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-French")
84
  model.to("cuda")
85
  chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�]'
86
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
79
 
80
  test_dataset = load_dataset("common_voice", "fr")
81
  wer = load_metric("wer")
82
+ processor = Wav2Vec2Processor.from_pretrained("Nhut/wav2vec2-large-xlsr-53-French")
83
+ model = Wav2Vec2ForCTC.from_pretrained("Nhut/wav2vec2-large-xlsr-53-French")
84
  model.to("cuda")
85
  chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�]'
86
  resampler = torchaudio.transforms.Resample(48_000, 16_000)