mdx-net VS stemroller

UVR does include support for demucs (including the latest version, v4); however, the model that OP is recommending is mdx-net, which is a completely different AI model. mdx-net can produce superior vocal stems, but it can separate into only two stems (vocals, other).

The only thing i changed was auto_lr_find: False i set it to : True , here https://github.com/kuielab/mdx-net/blob/main/configs/trainer/minimal.yaml

Would be possible to make this into a foobar2000 component https://github.com/stemrollerapp/stemroller

For those interested, Facebook's Demucs page (https://github.com/facebookresearch/demucs) gives performance comparison for several models including open-unmix.

See also: https://www.stemroller.com This runs as a local app on Windows and Mac.

This is a pay as you go service that works pretty well. This one is free and works slightly less better (IMO) than the first. Website makes it sound like you have to use their search function but you can just drag and drop audio files in.

Try Stemroller (https://github.com/stemrollerapp/stemroller). It can break an mp3 down into individual stems. Very CPU intensive though.

I usually try a few options to test for the best results, including Vocalremover and Spleeter, but also https://www.stemroller.com/

Stem Roller

I wonder why ubisoft hasn't used ai to split the tracks in rocksmith. There are tools like https://github.com/stemrollerapp/stemroller that can do it easily. DJs are doing this live with audio they are mixing. It would make the game more fun and realistic. I don't like hearing the original guitar over mine. I wish I could mute it and play solo.