amitaie

I looked at the implementation here and the FastPitch paper and i didn't understand how the use of interpolation won't ruin the pitch prediction in the case of unvoice in...

i'm working on different repo so it will be hard for me to report, but I still can't understand isn't it a problem to use continuous f0? when does the...

But if I understood correctly the ASR model is part of the model that comes back from build_model method, and in the training loop goes back to train mode: https://github.com/yl4579/StarGANv2-VC/blob/main/trainer.py#L156

i'm not using the same code, i did a lot of changes in order to insert it to my repo and way of work, i'll try to reproduce it on...

I will run few checks on the F0 model and the ASR model and report the insights that i have. But the ASR model does use dropout, and also normalization...

Took me some time but I have some results. I manged to fix the bug and change the ASR model to eval, i needed to fix small in-place line in...

actually I see that in the SoundStrom repo you started to do something like that: https://github.com/lucidrains/soundstorm-pytorch/blob/22d257d6b5241583e84619b7af6a634158aba426/soundstorm_pytorch/attend.py#L96-L99 but yo left the assert there and also i didn't understand why you divide...

> > sampling rate is 16kHz, and a strides value of 480 is used in MusicLM when the sampling rate is 24kHz. > > Yes you're right, for 16 kHz...

OK, i though you meant original from SoundStream, and in SoundStream paper they actually used 24000 sample rate.