qqpann
/

w2v_hf_jsut_xlsr53

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

qqpann commited on Mar 29, 2021

Commit

cd5d23c

·

1 Parent(s): 5451826

Update: resampler

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -95,7 +95,8 @@ model = Wav2Vec2ForCTC.from_pretrained("qqhann/w2v_hf_jsut_xlsr53")
 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.
 # We need to read the aduio files as arrays

 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) # JSUT is already 16kHz
+resampler = torchaudio.transforms.Resample(16_000, 16_000) # JSUT is already 16kHz
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays