What can be expected from training/finetuning?
#15
by
ssardorf
- opened
Hi! I'd love to venture into further training this model.
However, I haven't done much speech-synthesis work in the past, so I'd like to understand what's possible and what's not.
By pumping more training data into this model, would speech become more human-like? Or what would be the requirements for improving how human it sounds?