Best ensemble finder for a song script

by Vinctekan

 

https://drive.google.com/file/d/1LUtBsCSym1iDHqADEusmACs-LF2lNYLw/view?usp=sharing

 

Currently, this optimized version can find the best combo of 9, 3 minute audio files in about 2 minutes and 40 seconds in Colab.

 

 

Refactored best weighted ensemble finder by jarredou

https://drive.google.com/file/d/1Rm09z1wpj0Pi-6bFQ15u767n1XV95pDz/view?usp=sharing

 

“That's what I've used to find optimal weights for my MDX23 fork v2.5 update.

It's still Nelder-Mead based optimizer, but code is way more simple/clean than 1st version.

 

To use it, you need:

A dataset of clean sources (with exact same filename scheme than mvsep multisong dataset).

Process dataset mixtures with all the models you want to ensemble and put the outputs in different folders, 1 for each model (and still with exact same filename scheme than mvsep multisong dataset).

librosa and scipy python libs

then run (for example):

weight_finder_v2.py \

  --ref c:\reference_dataset \

  --est c:\InstVoc c:\bsrofo1296 c:\kimrofo \

  --stem vocals \

  --extension flac \

  --tracks 100

 

--ref is clean sources' folder path

--est is estimates (separations) folder paths (multiple inputs)

--stem is stem name (based on multisong dataset filename scheme)

--extension is audio file extension (flac/wav...)

--tracks is a number of tracks in a dataset.

 

 

It will process the datasets many times and change weights each time until it find the best balance. When finished, it will output weights scaled to 10 max value.

Warning: it can take hours (or even days, depending on the number of models to ensemble, size of dataset and resources of computer)

A python lib to align audio:

https://github.com/nomonosound/fast-align-audio”