Daniel Holler

> @danablend / @makorihi check out [#93 (review)](https://github.com/metavoiceio/metavoice-src/pull/93#pullrequestreview-1934338050) Have just been reading through it! I'll get it up on my system and add LoRAs to this as soon as possible,...

> @vatsalaggarwal > > > @danablend I think the main thing to keep in mind is: each row is composed of "text tokens | audio tokens | padding"... I think...

I have gotten LoRAs to train based off of @lucapericlp's awesome work. Gonna clean it up and prepare for review. Probably going to happen in the weekend.

> > I have gotten LoRAs to train based off of @lucapericlp's awesome work. > > Gonna clean it up and prepare for review. Probably going to happen in the...

> Yeah, and a 44.1/48khz wav or 256kbps mp3 works better… but, it’s unlikely the model would be able to produce an Irish accent regardless in one-shot, at least we...

> @danablend can you push your code to PR? I can have a look Hey @vatsalaggarwal, I realized that I had made a mistake and needed to build more code...

> Really hard to know where the issue is without seeing the code! I think it should be possible to finetune on a 16GB GPU but depends on your config...

> Really hard to know where the issue is without seeing the code! I think it should be possible to finetune on a 16GB GPU but depends on your config...

I'd be interested in contributing this in the future (few weeks from now) if nobody else does. @gururise would you be interested in working on this? Happy to collaborate, but...

@bluusun You are probably running a previous PyTorch version. Have you tried with torch==2.2.1?