Dumiiii commited on
Commit
a8857e4
1 Parent(s): 408febd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -8,7 +8,7 @@ model-index:
8
 
9
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
  should probably proofread and complete it, then remove this comment. -->
11
- ## This model achieves WER on common-voice ro test split of WER: 14.602631%
12
  # wav2vec2-xls-r-300m-romanian
13
 
14
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an common voice ro and RSS dataset.
@@ -73,7 +73,7 @@ processor = Wav2Vec2Processor.from_pretrained("Dumiiii/wav2vec2-xls-r-300m-roman
73
  model = Wav2Vec2ForCTC.from_pretrained("Dumiiii/wav2vec2-xls-r-300m-romanian")
74
  model.to("cuda")
75
 
76
- chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“]'
77
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
78
 
79
  # Preprocessing the datasets.
 
8
 
9
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
  should probably proofread and complete it, then remove this comment. -->
11
+ ## This model achieves WER on common-voice ro test split of WER: 12.457178%
12
  # wav2vec2-xls-r-300m-romanian
13
 
14
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an common voice ro and RSS dataset.
 
73
  model = Wav2Vec2ForCTC.from_pretrained("Dumiiii/wav2vec2-xls-r-300m-romanian")
74
  model.to("cuda")
75
 
76
+ chars_to_ignore_regex = '['+string.punctuation+']'
77
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
78
 
79
  # Preprocessing the datasets.