theverge.com/2019/11/5/20949338/vocal-isolation-ai-machine-learning-deezer-spleeter-automated-open-source-tensorflow

waxy.org/2019/11/fast-and-free-music-separation-with-deezers-machine-learning-library

github.com/deezer/spleeter

ok this hard

They always say this then you play it back and it’s low quality acapella with hi hats and a bunch of noise

yes but that's before artificial intelligence google tensor flow big data models were applied

Early

Isotope already has a plugin that does this

Need an application that automatically removes features that I don't like