Skip to content

Conversation

@khakers
Copy link
Owner

@khakers khakers commented Sep 8, 2023

Adds a dockerfile built for CUBLAS, which allows GPU acceleration in the encoding stage.

Adds a dockerfile built for CUBLAS, which allows GPU acceleration in the encoding stage.
@khakers
Copy link
Owner Author

khakers commented Sep 18, 2023

The current problems as I can recall them:
Uses an older CUDA version (11.8) due to errors in whisper.cpp builds with the newer version (I think the next release will fix these)
The Dockerfile is a bit of a hacked together mess

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants