-
https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.
XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG
- Joined on
2022-10-10
I figured I wasn't going to do anything leisurely today besides sleep, so I elected to work on an interleaved AR. Initially, I was going to say it was very much not fruitful, but after doing the…
436b67980e
skeleton for interleaving (I can't wrap my head around trying to compute the logits properly at the moment)
I suppose I have to train the AR from scratch if I want to increase the layer count. There's been no perceptible change in the model after training it about a day.
- I suppose that my naive…
81b05dabb9
accurate epoch metric is now reported (based on samples processed / length of dataset's paths, rather than naive assumptions)
The actual error itself should be fixed, I forgot to commit the change from a few days ago.
The underlying error I don't know, as that is more of an issue with DLAS itself. I would look into…
Should be fixed in commit 7fc8f4c45a2fbf259ae1ad6ca903752446d9e8be. I remembered I might have flubbered it up during cleanup of trying to make initialization faster (which was just from having a…
Verify that you have Embed Output Metadata disabled in the settings.
922404285c
fixed segfault from tts-c task token exceeding being too big (inserted it in the hypothetical svc task token because in reality that is never ever going to be a feasible task to train against)
4613781e23
integrated plot script, added tts-c task token to help the model be able to mix between normal VALL-E and VALL-E continuous
As an aside update:
- I've resumed training on my 7900XTX with the AR expanded to 24 layers instead of 12. No hitches so far.
- I should have gone with 18 layers instead to babystep, but…