jimregan commited on
Commit
0d51599
·
1 Parent(s): 7e7c35a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -27,7 +27,7 @@ model-index:
27
  # Wav2Vec2-Large-XLSR-Upper-Sorbian
28
 
29
  Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
30
- on the [Irish Common Voice dataset](https://huggingface.co/datasets/common_voice).
31
  When using this model, make sure that your speech input is sampled at 16kHz.
32
 
33
  ## Usage
@@ -75,7 +75,7 @@ wer = load_metric("wer")
75
  processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
76
  model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
77
  model.to("cuda")
78
- chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�„«»–]'
79
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
80
  # Preprocessing the datasets.
81
  # We need to read the audio files as arrays
 
27
  # Wav2Vec2-Large-XLSR-Upper-Sorbian
28
 
29
  Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
30
+ on the [Upper Sorbian Common Voice dataset](https://huggingface.co/datasets/common_voice).
31
  When using this model, make sure that your speech input is sampled at 16kHz.
32
 
33
  ## Usage
 
75
  processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
76
  model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
77
  model.to("cuda")
78
+ chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�„«»–]'
79
  resampler = torchaudio.transforms.Resample(48_000, 16_000)
80
  # Preprocessing the datasets.
81
  # We need to read the audio files as arrays