Replies: 2 comments 2 replies
-
Re-downloading the "large" model should get the new "large" model via whisper.cpp in SE. Yes, the new large model works really well in the one test I did :) |
Beta Was this translation helpful? Give feedback.
0 replies
-
Greetings. Delivered version SE 3.6.10 Beta. Loaded the large Whisper model. I understand correctly that the GPU is not used in this case, but the CPU is used? |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
openai/whisper#397
reading this thread new model for whisper seems to improves the error rate.
Beta Was this translation helpful? Give feedback.
All reactions