demucs

https://github.com/deezer/spleeter https://github.com/facebookresearch/demucs

Please go ahead! I'd love to see where it goes and would be willing to help out. I've already opened an issue to track "adding support for user-provided audio" as we discussed, see: https://github.com/omeryusufyagci/fast-music-remover/issues/... As for your question: it depends on the approach; Fast Music Remover currently uses DeepFilterNet, which has a deep learning approach and doesn't identify audio components as logical layers, which is why it's rather fast. Typically for that sort of requirements you'd want to work with a model like `demucs` (https://github.com/facebookresearch/demucs), that can identify individual audio components. That comes at great performance costs though. However, my vision for the core of FMR is to support multiple ML models and provide the optimal solution for user needs, without them worrying about these de

https://github.com/facebookresearch/demucs If you can train an instrument model on laugh tracks Demucs should do that.

For MIDI: https://github.com/Music-and-Culture-Technology-Lab/omnizart and https://basicpitch.spotify.com/ They work better if you apply some source separation before (e.g, https://github.com/sigsep/open-unmix-pytorch, https://github.com/facebookresearch/demucs, or https://mvsep.com) Still, I think the best results are from proprietary models (specifically https://www.ableton.com/en/manual/converting-audio-to-midi/ and https://www.celemony.com/en/melodyne/what-is-melodyne)

they've been on this wave for years. thanks to meta i have been creating instrumentals of some of my favorite songs with vocals https://github.com/facebookresearch/demucs

My partner plays violin and was looking for a version of Lindsey Stirling's Crystallize without the violin part (or rather, with it turned down.) I found plenty of tools online to do this, but they were all credit-based and a bit annoying to use. I eventually found they were mostly using Demucs from Facebook: https://github.com/facebookresearch/demucs Really nice tool if you need simple splitting of things like drums, vocals, etc. It's not perfect, but it's a great start.

demucs for the win. https://github.com/facebookresearch/demucs

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.

Demucs [1], one of the leading/SOTA systems, has an experimental 6-source model, `htdemucs_6s`, which adds piano and guitar: >We are also releasing an experimental 6 sources model, that adds a guitar and piano source. Quick testing seems to show okay quality for guitar, but a lot of bleeding and artifacts for the piano source. I also believe Audioshake [2] (a company in the space) is doing guitar separation as well. 1: https://github.com/facebookresearch/demucs 2: https://www.audioshake.ai/

I wonder if this would yield even better results if it were to be split into multiple tracks in the pre-processing stage with something like Demucs.[1] https://github.com/facebookresearch/demucs

Stemroller[1] is another audio track separator, based on demucs[2]. The demucs GH page has an accuracy comparison table with spleeter, demucs and others. [1]: https://github.com/stemrollerapp/stemroller [2]: https://github.com/facebookresearch/demucs

Maybe use demucs directly? https://github.com/facebookresearch/demucs

Musicians and studios don't generally tend to offer the public access to original stems for songs (why would they?) Say that you want to make a remix, mashup, or otherwise use sound-bytes from a song. The easiest thing to do is use a tool like Spleeter/Demucs to separate the source layers so that you can then further process them in your DAW. This is what I do, but I just use the Demucs CLI because it's simple enough. https://github.com/facebookresearch/demucs