EfficientAT VS free-music-demixer

Interesting, I attempted to do the same as you but stopped just shy of BPM matching.

However I did get sound similarity working using an audio tagging neural net [1]. I chopped off the first and last 15 seconds of every song in my collection and ran them all through this analysis which produces a ~520 dimensional vector. I then targeted specific endings I wanted to match and used Euclidian distance to find the closest matching song beginning.

YMMV but I thought it actually worked pretty well, I just never got to automating the BPM matching. I can try to look for my old script if you're interested :)

[1] https://github.com/fschmid56/EfficientAT

Hi HN,

Over the Christmas break I added multi-threading to the WASM Demucs module in freemusicdemixer

Demucs (v4 hybrid transformer) is a much higher quality model than the previous default, but it ran very slowly when limited to one worker: ~17 minutes for an average 4-minute song

I have since implemented multi-threading with WebWorkers.

If you raise the "MAX MEMORY" setting to 16 GB or 32 GB, your track will demix within 7-5 minutes, producing state-of-the-art results.

There is also support for the Demucs 6-source model which adds piano and guitar stems.

Please reach out and be loud about any bugs or UX issues you encounter!: https://github.com/sevagh/free-music-demixer/issues

* 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...