open-unmix-pytorch VS stemroller

In my first post, quite a lot of alternatives were discussed: https://news.ycombinator.com/item?id=36707877

The model I'm using is called Open-Unmix (https://github.com/sigsep/open-unmix-pytorch). In 2021, there was an update to Open-Unmix to include new weights, UMX-L, which made it perform better than it used to on the older weights (UMXHQ).

In the grand landscape of music demixing, I don't think UMX-L is near the top anymore.

_However_, the demixing performance of freemusicdemixer.com is very close to the full PyTorch performance of Open-Unmix UMX-L, despite the tricks I needed to get it working in the browser, such as splitting up the inference to operate on segments of the song, or making the LSTM operate on streaming segments rather than holding the entire track in the LSTM memory.

In my first release, I loaded and did inference on the entire track at once (like the PyTorch model), which frequently crashed or exceeded the 4GB WASM memory for medium or large-size tracks.

* Post-processing step (bigger impact)

I tried to tackle the post-processing step in my C++ code (which would win ~1 dB in quality across all targets) but it's too tricky for now [2]. Maybe some other day.

1: https://github.com/sevagh/free-music-demixer/blob/main/examp...

2: https://github.com/sigsep/open-unmix-pytorch/blob/master/ope...

Or open-unmix. I've found it performs better than spleeter in some of my tests.

There's maybe something useful for you here?

https://github.com/facebookresearch/demucs

https://github.com/sigsep/open-unmix-pytorch

https://github.com/bytedance/music_source_separation

https://github.com/deezer/spleeter

OpenUnmix ( is a neural network solution from Yuki Mitsufuji and Stefan Uhlich, music industry luminaries that work in Sony's core divisions.

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.