Aaron (Yinghao) Li

Has anyone tried to directly model the complex numbers instead of the phase and magnitude? What would be the problem if we model the real and imaginary parts directly?

Extremely weird DDP issue for train_second.py

38

So far [train_second.py](https://github.com/yl4579/StyleTTS2/blob/main/train_second.py) only works with DataParallel (DP) but not DistributedDataParalell (DDP). One major problem with this is if we simply translate DP to DDP (code in the comment section),...

Which model is 7B (Default) and which is 13B (Beta)?

12

Are models downloaded from `inference.sh` 7B (Default) or 13B (Beta)? I found the latter quite error prone and not stable, which is similar to what I'm observing now locally. I...

diffusion-based model results

1

Great work! Have you tested the performance of this codec on diffusion-based models such as SimpleTTS or DiTTo-TTS?