This is a Voice Model to be used with Retrieval-based-Voice-Conversion-WebUI.
This Includes the Model and the Index File.
It was Trained with 40k sample rate with the V2 Architecture with Pitch Guidance at 1000 Epochs.
To use put the .pth file the Weights folder and then the .index (Put it is in a folder already for you) file in the logs folder.
Description
FAQ
Comments (5)
Stable diffusion does voices now? This is new to me.
Very cool. Thanks.
This website allows all sorts of Models. I saw others posting their Voice Models on here (Plus some LLM models) so I posted Mine. Also btw this is for Retrieval-based-Voice-Conversion-WebUI (RVC) not Stable diffusion (If that was not obvious Enough).
@TheMelonGod Not obvious to me at all. The interface looks similar to Automatic1111, I'll look into it. Thanks.
@SL0TWRX Ah I see. The interface you see is used by many things it is called Gradio. The more you use open source tools the more you will see it.
@TheMelonGod That makes sense. Thanks for educating me.