DewiBrynJones
/

wav2vec2-large-xlsr-welsh

Automatic Speech Recognition

xlsr-fine-tuning-week

Model card Files Files and versions Community

DewiBrynJones commited on Apr 8, 2021

Commit

54c100e

•

1 Parent(s): 0d04ed7

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: Welsh XLSR Wav2Vec2 Large 53 (Bangor University)
   results:
   - task:
       name: Speech Recognition
@@ -91,7 +91,7 @@ model = Wav2Vec2ForCTC.from_pretrained("DewiBrynJones/wav2vec2-large-xlsr-welsh"
 model.to("cuda")
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\u2013\\u2014\\;\\:\\"\\\\%\\\\\\]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)

 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
+- name: Wav2Vec2-XLSR-53-Welsh (Bangor University)
   results:
   - task:
       name: Speech Recognition
 model.to("cuda")
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\u2013\\\\u2014\\\\;\\\\:\\\\"\\\\\\\\%\\\\\\\\\\\\]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)