-
demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation, but the goddamm motherfucker doesn't work.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
His songs are just separate 'clean' channels stored on the device. The custom uploads will use some machine learning to separate/isolate vocals from everything else and some beats. You can try the vocal isolation yourself with open source software: https://github.com/Anjok07/ultimatevocalremovergui
There might be one for drum/beat or instrument isolation as well but haven't run across it before. You could do it by hand but it would be very tedious. Isolating specific time ranges with an EQ just to get what you want. ML can do it much faster of course, still not perfect though. https://github.com/facebookresearch/demucs
Related posts
-
Romy & Fred again.. - Strong (Yelow Bootleg Remix) [2023]
-
A potentially better A.I. stem instrumentals tool than Hybrid Demucs, x-minus's mdx v2
-
I used an AI to remove the background music from the latest episode to hear the conversation between Red guy and Duck more clearly
-
Software for creating acapella from a track
-
Best way to extract a vocal stem from a song