[Discussion] Training model using one huge WAV file not 150

Hi! I'd like to train model in order to get better separation. I read that I need something like musdb for this but musdb syntaxis needs for me: 5 .wav files for each track (mixture, drums, basses, other, vocal), their .csv description (a table where n - number of rows describing each .wav location and duration in seconds) and .json metafile.

I couldn't find any API to generate my own track set and general .csv and .json files (not musdb 150 tracks) for training model.

I don't want to manually write .csv description for each track so I have an idea: what if I merge 1000-100000 .wav tracks into ONE huge .wav file and just use it for training model?

So, the question is: does 150x5 .wav files is the same as if I create only ONE set of 5 .wav files? Will ONE huge .wav file with duration for example 24 hours work as an input for training model?

Start by reading the issue's description of musdb inputs, including the five WAV files, CSV track descriptions, and JSON metadata. Check the training data entry points and determine whether a single concatenated 24-hour WAV file is supported; done would be a clear answer or a defined change request for custom dataset generation.

Written by the indexing model from the issue text.