Thank you for both your answers! My turn:
It's more about seeing where your mel loss ends up. Typically too small of a loss risks overtraining the model. My original rule of thumb…
Hello! Thank you very much for all this information.
If you don't mind me abusing of your kindness, I have a few more questions regarding the global fine tuning of a model, and I don't really…
Hey again! So the training has been running for about 8 hours now so I think it's safe to assume that the issue is fixed ^^What I did basically is reinstall everyhing by following the instructions…
Hey there! Thank you for your quick answer :) I'll investigate this and let you know!
Have a great rest of the day/night :)
I also just found out that there's a "Settings" tab in the web UI where you can change the sample batch size :)