RVC Studio
RVC Studio
I haven't released my plugin yet. Keep an eye out for this: https://github.com/SayanoAI/Comfy-RVC
Can you try extracting the zip file into it's own folder and point the training path to: "RVC-Studio/input/inoutfiles" Your files should be something like "RVC-Studio/input/inoutfiles/file1.wav"
Thanks for letting me know. I'll get people to install conda manually and have them run conda-start script instead.
this would be extremely useful for cloud serverless applications!
> Thanks but maybe you can start it later to aviod code conflicts because I'm changing the whole code structure recently. > > As for the main topic of this...
How are you rendering those graphs in audacity? I was not able to replicate this using the default mel spec in audacity (voice model applied, original, blank net_g): 
Did you do anything special with the settings? Why does mine look black? I'm using the default spectogram settings: 
I would remove fairseq and use contentvec.safetensors instead