Srinivas Billa
Srinivas Billa
Also for multiple languages, Vall-E X exists but no implementation. And Natural Speech 2 seems very promising. But implementation is on the way by lucidrains
Yeah Natural Speech 2 is amazing. I'm keeping a close eye on the implementation by lucidrains. It's being sponsored by Stability so if we're lucky he may provide a pretrained...
Btw if you want some more insight, there is a long thread here about mrq training vall e https://git.ecker.tech/mrq/ai-voice-cloning/issues/152 Apparently on a 4070 ti lol
This is nice @RuntimeRacer . Do you know what the differences are from the paper?
@RuntimeRacer I see. Yeah I would try train it myself if I can. I'm thinking of maybe adapting the code to Deepspeed/accelerate so that I can do nvme offloading. It...
@RuntimeRacer those are some Interesting graphs. I wonder why it converges so quickly.
Train goes down and valid goes up indicates overfitting but surely the dataset is not that small
To be fair it's almost 300k steps. Did you try inference?
I tried to run this on 8xA10 in 4 bit was getting this error. Unless I miscalculated, it should be able to fit in 8xA10(24gb) right? ``` ValueError: Some modules...
It did load on cpu, but I wasn't able to do inference. But ive uploaded the 4bit version here anyway in case anyone can test https://huggingface.co/eastwind/grok-1-hf-4bit