Replies: 2 comments 1 reply
-
|
It'd be kinda cool to find a way to separate background music from people talking. Especially when there's singing in some songs, it makes it questionable at times whether if that can be done. |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
Demucs exists which can do this, I think... |
Beta Was this translation helpful? Give feedback.
-
|
Hey any one know answer for this? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
UVR already can do lots of separation such as vocals, music, de-reverb, de-echo, etc..
Is there a MODEL that allow to separate multiple speakers? for example:
Sometimes in Podcast 2 or more people are talking together, separating each human voice could be nice.
I believe Meta have something related, you can read more about it here:
voice separation model that distinguishes multiple speakers simultaneously
Since I'm not sure if there is already such model for UVR I decided to ask in here.
Maybe there is already such MODEL to download but if so, I missed it.
If not... it will be amazing to have this option in the future to separate multiple speakers.
Please share / update in here if there are news on this subject, thanks ahead! 🙏
Beta Was this translation helpful? Give feedback.
All reactions