• Our site rules have went through some updates and changes recently! Please take a moment to read over the changes (Rules 2-4) here!

New open source machine learning tool can quickly split instrumentals & vocals from a song

Ulysses

from VOICeVIO
May 4, 2018
39
github.com
Just tried this. Works well as a free, open-source tool. Process a 4 min song in 20s with 6GB memory used (CPU mode).
In most cases the result is still a bit worse than some commercial tool's output. But it can still be improved if someone would train a better model.
 
  • Like
Reactions: cafenurse

Users Who Are Viewing This Thread (Users: 0, Guests: 0)