search

gitmylo / audio-webui

A webui for different audio related Neural Networks
MIT License
1.02k stars 95 forks source link

[FEATURE REQUEST] RVC 2.0 48k Sample rate? #46

Open Ph0rk0z opened 1 year ago

Ph0rk0z commented 1 year ago

There are now 48k v2 models and a fork with a hybrid training feature. Are they any better?

https://github.com/Mangio621/Mangio-RVC-Fork

Files from YT are generally 48k. The only issue is the demucs models mainly do 44.1, although demucs can supposedly support 24bit. https://github.com/facebookresearch/demucs/issues/288

Am unsure how upsample vs downsample works out for final output.

gitmylo commented 1 year ago

They might be better, i'll implement it. Not immediately though, i'm currently making an improved install system.

Ph0rk0z commented 1 year ago

No worries. For install I actually reused my nvida environment and added the handful of extra packages so I always bypass the venv entirely.

nekogecko2 commented 1 year ago

I'd like to request adding the option of using the "mango-crepe" algorithm too for training and generating

gitmylo commented 1 year ago

While adding v2 48k i realized v1 48k doesn't work, i have some fixing to do

Ph0rk0z commented 1 year ago

Yea.. you're right. I had tried V1 48k and assumed something was wrong with my system instead.

gitmylo commented 1 year ago

Yeah, once i fix that, v2 48k should also work

Ph0rk0z commented 1 year ago

I will try to re-run some datasets and see if the quality is higher. If only any demucs supported 48k. With already clean samples or self-recorded audio it will probably be a nice improvement.

Ph0rk0z commented 1 year ago

48k failed for me on training. I got the d/s converted. The 2nd wav folder doesn't generate files. The one where the # of items would be double. All the other ones happen but training goes down on tensor shape/size.

gitmylo commented 1 year ago

48k failed for me on training. I got the d/s converted. The 2nd wav folder doesn't generate files. The one where the # of items would be double. All the other ones happen but training goes down on tensor shape/size.

That message above was one message not 2, it said once i fix that, v2 48k should also work, but i haven't worked on fixing it yet.

Ph0rk0z commented 1 year ago

Fair, I'm just saying how far I got testing it.

halilergul1 commented 1 year ago

48k failed for me on training. I got the d/s converted. The 2nd wav folder doesn't generate files. The one where the # of items would be double. All the other ones happen but training goes down on tensor shape/size.

That message above was one message not 2, it said once i fix that, v2 48k should also work, but i haven't worked on fixing it yet.

Hi Mylo!, is v2 48k working currently or shall we wait?

gitmylo commented 1 year ago

48k failed for me on training. I got the d/s converted. The 2nd wav folder doesn't generate files. The one where the # of items would be double. All the other ones happen but training goes down on tensor shape/size.

That message above was one message not 2, it said once i fix that, v2 48k should also work, but i haven't worked on fixing it yet.

Hi Mylo!, is v2 48k working currently or shall we wait?

Not yet, i haven't really been working on it, 48k works in inference by the way, just not during training.