Stephane Mallette
Stephane Mallette
I tried with another video that was only 2 minutes and it worked flawlessly. I tried modifying the max audio samples in case of overlapping, the other presets as well...
I did not monitor, you might be right. I'll check that out thanks
Wav2Lip would potentially work or facefusion codes that they are using to do so with another face.
Thats called dependency hell, I suggest you backup or clone your env and try with conda for TTS and see where it brings you
Honnestly, I have to say, you impress me so much. The amount of details you put into this is astonishing. Feel free to contact me for anything. I am pretty...
Long story short, it was brutal to make this work 😓 I finally managed to get in, then I couldn't see my models but I manage to search around forks...
Oh its ok no worries haha it's a Ryzen 7800x3D and 3060 Ti (4000 Cuda) Do you have an environment that works with it that you could upload? That would...
Ill try it with docker -------- Original message -------- From: RVC Studio ***@***.***> Date: 2024-04-29 00:29 (GMT-05:00) To: SayanoAI/RVC-Studio ***@***.***> Cc: Stephane Mallette ***@***.***>, Author ***@***.***> Subject: Re: [SayanoAI/RVC-Studio] Greyed...
error: could not find git for clone of pybind11-populate
Detecting main repo language... Migration: no config.json detected Migration: no .docker/docker-compose.yaml detected Could not detect language - using default base image #0 building with "default" instance using docker driver #1...