Yehor
/

w2v-bert-uk-v2.1

Automatic Speech Recognition

Model card Files Files and versions

Yehor commited on 24 days ago

Commit

a8b1bf0

·

verified ·

1 Parent(s): 2c002d0

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -92,7 +92,7 @@ for path in paths:
 # Transcribe the audio
 inputs = processor(audio_inputs, sampling_rate=sampling_rate).input_features
-features = torch.tensor(inputs).to(device)
 with torch.inference_mode():
   logits = asr_model(features).logits

 # Transcribe the audio
 inputs = processor(audio_inputs, sampling_rate=sampling_rate).input_features
+features = torch.tensor(inputs).half().to(device)
 with torch.inference_mode():
   logits = asr_model(features).logits