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

Investigate Word-level timestamps for discarding processed audio #330

Open
makaveli10 opened this issue Jan 21, 2025 · 0 comments
Open

Investigate Word-level timestamps for discarding processed audio #330

makaveli10 opened this issue Jan 21, 2025 · 0 comments

Comments

@makaveli10
Copy link
Collaborator

In the faster-whisper backend, current impl considers the last segment as incomplete to be able to correctly discard processed audio by assuming the last segment might have a word cut off.
The idea is to use word level timestamps and just keep the audio for the last word.
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
1 participant
@makaveli10