anas
/

wav2vec2-large-xlsr-arabic

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

anas commited on Mar 28, 2021

Commit

1dbd4b3

•

1 Parent(s): aa74d29

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -86,7 +86,7 @@ processor = Wav2Vec2Processor.from_pretrained("anas/wav2vec2-large-xlsr-arabic")
 model = Wav2Vec2ForCTC.from_pretrained("anas/wav2vec2-large-xlsr-arabic/")
 model.to("cuda")
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\؟\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\'\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\☭\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\«\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\»\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\؛\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\—\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ـ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\_\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\،\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)

 model = Wav2Vec2ForCTC.from_pretrained("anas/wav2vec2-large-xlsr-arabic/")
 model.to("cuda")
+chars_to_ignore_regex = '[\,\؟\.\!\-\;\\:\'\"\☭\«\»\؛\—\ـ\_\،\“\%\‘\”\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)