open-unmix-pytorch VS spleeter

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.

virtual dj and others stem separator is shrinked model of this https://github.com/deezer/spleeter you will get better results downloading original + their large model.

I have used multiple tools at this point. It depends on the scene. I use https://ultimatevocalremover.com/, https://github.com/deezer/spleeter/, iZotope RX. There are also multiple options online, I would personally recommend https://vocalremover.org/.

I tried to use it but I had some issues as others in the thread.

I have tried many sources and method over the years and settled on spleeter [0]. Works well even for 10+ minute songs, varying styles from flamenco to heavy metal.

[0] https://github.com/deezer/spleeter

Spleeter is pretty good https://github.com/deezer/spleeter. Apparently it is used in some dj applications

Haha GitHub and command lines and all can be confusing, but it’s certainly worth the effort because it lets you do everything for free.. here’s the online tutorial: https://github.com/deezer/spleeter/wiki/1.-Installation

Chopped from their website Simple Stems is a quick and easy way to decompose any audio into it’s constituent parts. The plugin uses the well established Spleeter algorithm by Deezer to deconstruct songs into 2, 4 or 5 stems. The results are stunning, though more complicated mixes and live recordings are not always perfectly decomposed.

I was going to post basic pitch from Spotify but it looks like billconan beat me to it. That said I can give you a bit more advice. The Spotify basic pitch model isn't too good at multi-track input. It's capable of it, but you may actually get better results if you separate out the tracks first and then run them individually through the basic pitch model.

In order to do this you can use a source/stem separation model like spleeter (https://github.com/deezer/spleeter) and then run the basic pitch model (or any other midi transcription model). There's other you can try which may yield better results, for example: (https://github.com/Music-and-Culture-Technology-Lab/omnizart)

Either way the key words you want to be looking for are "midi transcription" and "stem separation", should help you find more models to try for both steps. Good luck! :)