openai
/
whisper-tiny.en
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md (#3) 

- Update README.md (933dd954d44445fa823390fd4ceeeed6049bcc35)


Co-authored-by: Luigi Liu <Luigi@users.noreply.huggingface.co>
This commit is contained in:
Arthur Zucker 2022-11-28 08:32:41 +00:00 committed by system
parent b8d7ffd4a8
commit f3b5e97e6e
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -115,7 +115,7 @@ The "<|en|>" token is used to specify that the speech is in english and should b
>>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features >>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features
>>> # Generate logits >>> # Generate logits
>>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]]).logits >>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]])).logits
>>> # take argmax and decode >>> # take argmax and decode
>>> predicted_ids = torch.argmax(logits, dim=-1) >>> predicted_ids = torch.argmax(logits, dim=-1)
>>> transcription = processor.batch_decode(predicted_ids) >>> transcription = processor.batch_decode(predicted_ids)