bayartsogt
/

wav2vec2-large-xlsr-mongolian

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

bayartsogt commited on Mar 20, 2021

Commit

1de0fb7

•

1 Parent(s): 23378e6

editing regex

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -86,7 +86,8 @@ processor = Wav2Vec2Processor.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mo
 model = Wav2Vec2ForCTC.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mongolian")
 model.to("cuda")
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'  # TODO: adapt this list to include all special characters you removed from the data
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.

 model = Wav2Vec2ForCTC.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mongolian")
 model.to("cuda")
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\'h\«\»]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.