Difference between model checkpoints

AppleHolic / source_separation

Deep learning based speech source separation using Pytorch

Apache License 2.0

312 stars 45 forks source link

Difference between model checkpoints #25

Closed roudimit closed 3 years ago

roudimit commented 4 years ago

Hi,

Thank you for this great project and for uploading the model weights!

What is the difference between first_voice_bank.best.chkpt and second_voice_bank.best.chkpt in the Google Drive folder for 'General Voice Source Separation'?

These checkpoints are from the training with Audioset data augmentation, right?

AppleHolic commented 3 years ago

Yes those are trained with data augmentation. And, second one gets more training time and better result. I recommend using second one.

AppleHolic commented 3 years ago

Close this issue