Hugging Face's logo

manandey
/
wav2vec2-large-xlsr-_irish

Automatic Speech Recognition Transformers PyTorch JAX
Irish
wav2vec2 audio speech xlsr-fine-tuning-week hf-asr-leaderboard Eval Results Inference Endpoints
Model card Files Community
manandey commited on
Commit
45d2d91
β€’
1 Parent(s): 81a3094

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -64,7 +64,7 @@ wer = load_metric("wer")
64
  processor = Wav2Vec2Processor.from_pretrained("manandey/wav2vec2-large-xlsr-_irish")
65
  model = Wav2Vec2ForCTC.from_pretrained("manandey/wav2vec2-large-xlsr-_irish")
66
  model.to("cuda")
67
- chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\β€œ\\%\\β€˜\\”\\οΏ½\\’\\–\\(\\)]'
68
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
69
  # Preprocessing the datasets.
70
  # We need to read the aduio files as arrays
64
  processor = Wav2Vec2Processor.from_pretrained("manandey/wav2vec2-large-xlsr-_irish")
65
  model = Wav2Vec2ForCTC.from_pretrained("manandey/wav2vec2-large-xlsr-_irish")
66
  model.to("cuda")
67
+ chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\β€œ\%\β€˜\”\οΏ½\’\–\(\)]'
68
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
69
  # Preprocessing the datasets.
70
  # We need to read the aduio files as arrays