63 supporters
New algorithms at MVSep.com

New algorithms at MVSep.com

Nov 12, 2021

We have three big news:

  • We had to move to a new server due to lack of space on the old one. Positive effect - the GPU has been changed to a more powerful one with more memory. As a result, the waiting queues have decreased and there are fewer errors associated with a lack of GPU memory.

  • A new algorithm has been added Ultimate Vocal Remover (UVR). It splits the track into two parts, music and vocals. UVR usually does it better than spleeter. There are a lot of models and different settings in the original UVR. We have chosen one of the best models and optimal settings. Perhaps later, a flexible choice of settings for the algorithm will be added.

  • The winner of the Music Demuxing Challenge has finally released his code. We added its models to the site under the names Demux3 Model A and Demux3 Model B. Demux3 Model B gives a better result, and works better for bass and drums comparing to other models, but is slightly inferior in vocals to the MDX-B algorithm.

Below is an updated table comparing the quality of algorithms (data for UVR are not available). The values ​​in the table are calculated on private Music Demuxing Challenge dataset (available only to organizers). The higher the value, the better the algorithm works.

Enjoy this post?

Buy ZFTurbo a coffee

More from ZFTurbo