Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

It always uses me to do the calculations instead of the GPU. #332

Open
melerodev opened this issue Jan 31, 2025 · 2 comments
Open

It always uses me to do the calculations instead of the GPU. #332

melerodev opened this issue Jan 31, 2025 · 2 comments

Comments

@melerodev
Copy link

I have tried Faster-Whisper with docker run -it --gpus all -p 9090:9090 ghcr.io/collabora/whisperlive-gpu:latest, but it keeps using my CPU instead of GPU.

Image
@makaveli10
Copy link
Collaborator

Hello, thanks for using WhisperLive! Can you check the gpu utilisation as well?

@melerodev
Copy link
Author

I solved it, the problem was that docker did not accept the GPU. A question, what do I have to modify so that the language at the time of translating the transaction is in the language I want?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@makaveli10 @melerodev