Zero_Shot_Audio_Source_Separation icon indicating copy to clipboard operation
Zero_Shot_Audio_Source_Separation copied to clipboard

How can train using my own dataset

Open Hope1337 opened this issue 1 year ago • 2 comments

Same as title : How can train using my own dataset ?

Hope1337 avatar Dec 24 '23 07:12 Hope1337

Hi, sorry for the late reply.

You need to revise or refer to the data_processor.py file to change the dataset loader and dataset classes. I use the "LGSPDataset" module to process the audioset data, so if you want to use our dataset like a similar way. You can take a look on that.

If you already get the separation training data (i.e., both mixture and separation/source tracks), things might become more easier because you don't need mix the data but directly trained with targets.

RetroCirce avatar Jan 24 '24 14:01 RetroCirce

I'll try, thanks <3

Hope1337 avatar Jan 27 '24 06:01 Hope1337