Commit
•
957677a
1
Parent(s):
ecd5620
Closed bracket in whisper-small
Browse filesClosed bracket in whisper-small english to english example
README.md
CHANGED
@@ -227,7 +227,7 @@ The "<|en|>" token is used to specify that the speech is in english and should b
|
|
227 |
>>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features
|
228 |
|
229 |
>>> # Generate logits
|
230 |
-
>>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]]).logits
|
231 |
>>> # take argmax and decode
|
232 |
>>> predicted_ids = torch.argmax(logits, dim=-1)
|
233 |
>>> transcription = processor.batch_decode(predicted_ids)
|
|
|
227 |
>>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features
|
228 |
|
229 |
>>> # Generate logits
|
230 |
+
>>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]])).logits
|
231 |
>>> # take argmax and decode
|
232 |
>>> predicted_ids = torch.argmax(logits, dim=-1)
|
233 |
>>> transcription = processor.batch_decode(predicted_ids)
|