joaoalvarenga
/

wav2vec2-large-xlsr-portuguese

Automatic Speech Recognition

portuguese-speech-corpus

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

joaoalvarenga commited on Mar 24, 2021

Commit

98fedef

•

1 Parent(s): 2c9efbe

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -93,7 +93,7 @@ processor = Wav2Vec2Processor.from_pretrained("joorock12/wav2vec2-large-xlsr-por
 model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-portuguese")
 model.to("cuda")
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\'\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
@@ -123,7 +123,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
-**Test Result (wer) **: 15.734702%
 ## Training

 model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-portuguese")
 model.to("cuda")
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\'\\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
+**Test Result (wer)**: 15.734702%
 ## Training