Aaron (Yinghao) Li

Maybe I’ll create a new branch in the PL-BERT repo for multilingual processing scripts. Chinese and Japanese definitely needs to be processed separately with their own logics. @mzdk100 If you...

@rjrobben I have created a slack channel for this multilingual PL-BERT: https://join.slack.com/t/multilingualstyletts2/shared_invite/zt-2805io6cg-0ROMhjfW9Gd_ix_FJqjGmQ

Also https://github.com/yl4579/PL-BERT/issues/22 this maybe helpful, if anyone could try it out.

@fakerybakery I can make this channel generally StyleTTS2-related if it is better. I can change the title to StyleTTS 2 instead.

Yeah I've already done that. There's a channel about multilingual PLBERT.

It expires every 30 days I don't know if there's a better to get a permanent link.

Thanks for your fix, but what does `.squeeze(0)` do? Doesn’t it squeeze over the batch dimensions and cause issues?

So does it mean it's probably just redundant? Does it still work with batch size greater than 1? Also it would be great if you could implement gradient accumulate for...

Can you be sure they’re on the same machine with the same library and everything, except the GPU difference?

@devidw Have you tried to match the CUDA driver version as well? Have you tried the docker version?