StarGANv2-VC icon indicating copy to clipboard operation
StarGANv2-VC copied to clipboard

How to deal with using non training data for inference, and the inference results are not realistic enough to restore

Open Nanshanelectrician opened this issue 1 year ago • 2 comments

How to deal with using non training data for inference, and the inference results are not realistic enough to restore

Nanshanelectrician avatar Dec 11 '23 12:12 Nanshanelectrician

Can you be more specific? Do you mean unseen speakers? Unseen samples? What kind of input that is not in training data?

yl4579 avatar Dec 12 '23 03:12 yl4579

I use two of my own audio files, hoping that A will imitate what B says. The output result obtained does not seem to be what A said, so it feels unreal

Nanshanelectrician avatar Dec 12 '23 09:12 Nanshanelectrician