gorkemgoknar commited on
Commit
dce0916
·
1 Parent(s): 5121291

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -69,7 +69,7 @@ model = Wav2Vec2ForCTC.from_pretrained("gorkemgoknar/wav2vec2-large-xlsr-53-turk
69
  model.to("cuda")
70
 
71
  #Note: Not ignoring "'" on this one
72
- chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�]'
73
 
74
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
75
  # Preprocessing the datasets.
@@ -95,4 +95,3 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
95
  **Test Result**: TBD %
96
  ## Training
97
  The Common Voice `train` and `validation` datasets were used for training. Additional 5 Turkish movies with subtitles also used
98
- The script used for training can be found [here](https://colab.research.google.com/drive/1hesw9z_kFFINT93jBvGuFspOLrHx10AE?usp=sharing)
 
69
  model.to("cuda")
70
 
71
  #Note: Not ignoring "'" on this one
72
+ chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�]'
73
 
74
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
75
  # Preprocessing the datasets.
 
95
  **Test Result**: TBD %
96
  ## Training
97
  The Common Voice `train` and `validation` datasets were used for training. Additional 5 Turkish movies with subtitles also used