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

Label different speakers #202

Closed
savchenko opened this issue Nov 29, 2022 · 2 comments
Closed

Label different speakers #202

savchenko opened this issue Nov 29, 2022 · 2 comments
Labels
duplicate This issue or pull request already exists

Comments

@savchenko
Copy link

Might be a stretch, but would it be possible to label different speakers if audio has >1 person talking?

This would come handy for conference recordings with multiple presenters, etc.
@savchenko
Copy link
Author

Thinking about possible implementation, the simplest one might be to label based on the audio channel.

Say we have a stereo recording:

  1. Recognize L/R separately
  2. Label accordingly
  3. Done

@ggerganov ggerganov added the duplicate This issue or pull request already exists label Dec 1, 2022
@ggerganov
Copy link
Owner

Stereo-diarization is already implemented - see #64
I have some other ideas in mind for general diarization, but low-priority for the moment.

mattsta pushed a commit to mattsta/whisper.cpp that referenced this issue Apr 1, 2023
@jibinmathew69 @jongwook
Add model_dir to arguments (ggerganov#202)
0b1ba3d 
* Add model_dir to arguments

* minor formatting change

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
duplicate This issue or pull request already exists
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@savchenko @ggerganov