indonesian-nlp
/

wav2vec2-large-xlsr-indonesian

Automatic Speech Recognition Transformers PyTorch JAX

Indonesian wav2vec2 audio speech xlsr-fine-tuning-week Eval Results Inference Endpoints

Model card Files Files and versions Community

cahya commited on Mar 29, 2021

Commit

c88e967

•

1 Parent(s): e74c80d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -86,7 +86,7 @@ processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-large-xls
 model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline")
 model.to("cuda")
-chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)

 model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline")
 model.to("cuda")
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\'\”\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)