ceyda
/

wav2vec2-large-xlsr-53-turkish

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

ceyda commited on Mar 29, 2021

Commit

79bc0c7

•

1 Parent(s): 2d0e4e3

Update README.md

fix chars_to_ignore weirdness

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -86,7 +86,7 @@ processor = Wav2Vec2Processor.from_pretrained("ceyda/wav2vec2-large-xlsr-53-turk
 model = Wav2Vec2ForCTC.from_pretrained("ceyda/wav2vec2-large-xlsr-53-turkish")
 model.to("cuda")
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\'\\\\`…\\\\]\\\\[\\\\&\\\\’»«]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.

 model = Wav2Vec2ForCTC.from_pretrained("ceyda/wav2vec2-large-xlsr-53-turkish")
 model.to("cuda")
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\‘\”\'\`…\]\[\’»«]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.