https://github.com/deezer/spleeter
https://news.ycombinator.com/item?id=21431071
An example: https://soundcloud.com/alezzzz/can-halleluwah-drums-extracted
The Deezer source separation library
Quick start
Want to try it out ? Just clone the repository and install a Conda environment to start separating audio file as follows:
git clone https://github.com/Deezer/spleeter conda env create -f spleeter/conda/spleeter-cpu.yaml conda activate spleeter-cpu spleeter separate -i spleeter/audio_example.mp3 -p spleeter:2stems -o output
You should get two separated audio files (vocals.wav and accompaniment.wav)
in the output/audio_example folder.
For a more detailed documentation, please check the repository wiki