Ruobai Wang

Results 4 comments of Ruobai Wang

@keicoon Not that problem... It is just something wrong with train_multi_gpus.py, I think, because train.py is fine.

> I think you still using the sanity_check = True, this is only a very small dataset, I got the same result. can you try the sanity_check = False ?...

@tmulc18 I think normalization is somehow important. When I try to eval.py with norm=None, the result is a mess (even for the pretrained model from the tacotron author) When I...