Forkoz

His bark is out of date and has no custom commits. You can just re install from the main repo. What he probably did was implement other things for voice...

RVC is a model that trains on pitches from your target and then "corrects" the audio you feed it to match them. So your not so good TTS output sounds...

That webui lets you clone with bark and run RVC over it for really good results. Unfortunately nobody has taken this process and used it for AI chat TTS.

You clone with bark or use some other similar TTS output and then you use the RVC model over it. I already have NPZ to try to use in bark...

They all seem to do what the settings imply.

I think that's only websearch and very backend dependent. I meant for it to pull a more general URL like say this github issue sans passing it through a search...

Cool, I will have to deal with the chat completion then. Sucks, maybe it's something for the future. Most larger models seem to "get" using tools. Some even figured out...

The model loading with whisperX is about 6gb but it goes up on inference. I tried to add model.half() in the model loading code too but there was no difference....

https://files.catbox.moe/azwyj4.mov here is what it does on my machine. I wonder why the CPU use is so high as well.

Anyone gotten it working in comfyui? ``` backend='nexfort' raised: CompilationError: at 47:12: tmp24 = tmp21 * tmp7 tmp25 = tmp24 + tmp9 tmp26 = 47 + ((-1)*x2) tmp27 = tmp26.to(tl.float32)...