8000 Seperation on more than 2 person audio · Issue #7 · dmlguq456/SepReformer · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Seperation on more than 2 person audio #7

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
Open
MonolithFoundation opened this issue Oct 12, 2024 · 3 comments
Open

Seperation on more than 2 person audio #7

MonolithFoundation opened this issue Oct 12, 2024 · 3 comments

Comments

@MonolithFoundation
Copy link

If 4 or maybe 25 people audio, does SepReformer can work?
@dmlguq456
Copy link
Owner

We plan to expand training to support up to four speakers in the future, but the current version of SepReformer can only separate two speakers. For now, if there are overlapping voices from three or more speakers, we recommend segmenting the audio so that only two voices overlap at a time for processing.

@MonolithFoundation
Copy link
Author
MonolithFoundation commented Oct 15, 2024 •
edited
Loading

the overlap you mean like

---
---

or

---
     ---

this way

@dmlguq456
Copy link
Owner

I was referring to the former case.

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
@dmlguq456 @MonolithFoundation
0