mrq
-
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
Block a user
a22534e8f4
layer skip training implemented (need to gut the inferencing from the repo, and to actually see if the model can benefit from this)
ccf71dc1b6
added option to load from a model state dict directly instead of a yaml (to-do: do this for LoRAs too), automatically download the default model if none is provided
92e6bff6dc
actually ar temp 0.5 with rep pen 1.125 seems to have the benefits of better outputs without it degrading some of the time but not all the time
910571ad34
too brainlet to diagnose why low temp / greedy sampling is randomly unstable some of the time
8eb9a4056b
modified default arguments (ar temp = 0 and rep pen = 1.125 seems to be stable, at least given the few things i tested), do not pass top k/top p/min p to NAR even though technically none of those things should matter when greedy sampling
1a02cd5bce
modify demo template to say F5 instead of YourTTS, swap LoRA comparison around to make the lora'd the base file, and the no-lora the suffix'd file
71731ed785
added prefixing with silence (was to test something, currently hidden under cfg.experimental=True)
6b04c13c56
print warning if audio promtpless inferencing with low AR temp (it really doesn't like low temps / greedy sampling)
c8f31db1de
default to greedy sample AR (i should probably test this more but it seems to pass my harvard sentences and tongue twisters)
fc8dfd8617
made greedy AR sampling viable (and preferable), with caveats (per comment in vall_e.models.ar_nar)