🚩 Report: Ethical issue(s)
#10
by badasbilly - opened
The uploaders of this model seem to be representing it as their own original work regarding the audio generation; however, it seems like they're actually just leveraging VITS and VQGAN with their own semantic encoding. It's dishonestly represented.
PoTaTo721 locked this discussion
PoTaTo721 unlocked this discussion
Stardust-minus locked this discussion
Stardust-minus unlocked this discussion
Stardust-minus changed discussion status to closed
Any proof? Quite confusing