demucs audio separation with Cuda support on Freebsd with Podman

[NapoleonWils0n]

I have just added demucs for audio separation with Cuda support
to my Freebsd Cuda project

GitHub - adefossez/demucs: Code for the paper Hybrid Spectrogram and Waveform Source Separation

Code for the paper Hybrid Spectrogram and Waveform Source Separation - adefossez/demucs

github.com

GitHub - NapoleonWils0n/freebsd-cuda: Run Linux command line and gui applications on FreeBSD with full Nvidia Cuda hardware acceleration.

Run Linux command line and gui applications on FreeBSD with full Nvidia Cuda hardware acceleration. - NapoleonWils0n/freebsd-cuda

github.com

Demucs is a state-of-the-art music source separation model, currently capable of separating drums, bass, and vocals from the rest of the accompaniment.

This is useful is you want to separate the vocals from the background music from a video's audio track

a use case might be if you recorded a video with the radio on in the background
and you need to remove the music so you can upload the video to youtube and not get any copyright issues due to the music

or if you want to strip out the vocals and have just the music to use for a karaoke session