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.

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

[Question] Does whisper maintain context between files? #2398

Open
UsernamesLame opened this issue Aug 31, 2024 · 2 comments
Open

[Question] Does whisper maintain context between files? #2398

UsernamesLame opened this issue Aug 31, 2024 · 2 comments

Comments

@UsernamesLame
Copy link
Contributor

If I wanted to run whisper across multiple files with confidential data, would it be safe to do so? Or does whisper maintain context between each file?

I can't find any definitive information about this. I just want to ensure I can load the model once and keep feeding it new files instead of doing a per context model load.

@UsernamesLame UsernamesLame changed the title Does whisper maintain context between files? [Question] Does whisper maintain context between files? Aug 31, 2024
@hsinatfootprintai
Copy link

@UsernamesLame I think you can check out release version of improving whisper.cpp especially for batch audio file processing. the performance is quiet gook. we planned to release its source code soon, but you can try the container image first. https://hub.docker.com/r/footprintai/cockburncli

@UsernamesLame
Copy link
Contributor Author

@UsernamesLame I think you can check out release version of improving whisper.cpp especially for batch audio file processing. the performance is quiet gook. we planned to release its source code soon, but you can try the container image first. https://hub.docker.com/r/footprintai/cockburncli

Any plans on the code drop? Also do you know if context is maintained?

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

No branches or pull requests

2 participants