I just discovered this repo, it looks really useful for creating AI voices
Tried this yesterday and got it installed and i was able to run it but it took some 20-30 gb and the cloning didn’t work. It couldn’t access my audiofiles. error 2 iirc. Someone made a video with almost the same probs… -> https://yewtu.be/watch?v=lm6AGTiQ25c
I’m going to try this out, but if it’s using that much VRAM I might be out of luck
if you refer to the 20-30 gb it’s disk space i meant. it used more than 30gb though.
Dam, I have this issue:
File "/home/st/.pyenv/versions/3.10.12/lib/python3.10/json/encoder.py", line 179, in default raise TypeError(f'Object of type {o.__class__.__name__} ' TypeError: Object of type PosixPath is not JSON serializable [end of output]note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for pyworld
what repository? maybe pip install pyworld? i’m having a hard time with fulfilling requirements all the time. (i can’t code, i tried…)
This GUI installed just fine --> https://github.com/JonathanFly/bark
Did you try it? For me Bark isn’t usable. It’s too robotic and the best results i get with the tts-fast (https://github.com/152334H/tortoise-tts-fast) but i was only able to install it on one computer with W10 and no gpu support. On the other machine i couldn’t get the requirements satisfied at all.
Same here: https://git.ecker.tech/mrq/ai-voice-cloning but i’m only on a GTX1080.
I had issues getting to run, I’ll come back to it. I have other ways to generate bark audio. I found bark to be by far the most natural sounding, it just sounds like it was recorded on a pc mic from 1999. Silero, elevenlabs, sounds monotone to me.
I haven’t tried Tortoise yet, I’ll have to try that!