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

Live Stream audio #670

Closed
MartinEmilEshack opened this issue May 18, 2021 · 2 comments
Closed

Live Stream audio #670

MartinEmilEshack opened this issue May 18, 2021 · 2 comments

Comments

@MartinEmilEshack
Copy link

My input audio will be recorded and might reach an hour or two of length. I'm also planning to host the model on a remote host. Uploading and processing an audio file that big will take so much time.

Is it possible to give the model a live stream audio? or maybe keep the same person-id for different small files?

If not I have a question
What is the largest length of audio file with maximum number of persons that the model can process without loosing accuracy?
@hbredin
Copy link
Member

hbredin commented May 18, 2021

Is it possible to give the model a live stream audio? or maybe keep the same person-id for different small files?

Online speaker diarization is something that is not currently supported in pyannote.audio.
Regarding speaker tracking, it is feasible with pyannote.audio but not available out of the box.
See related issues #391 and #651.

@hbredin hbredin closed this as completed May 18, 2021
@MartinEmilEshack MartinEmilEshack mentioned this issue Jul 2, 2021
Closed
@hbredin
Copy link
Member

hbredin commented Aug 25, 2021

FYI, @juanmc2005 just released some code to perform live speaker diarization.

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
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@hbredin @MartinEmilEshack