mrq 5fe01ffc6c more notes / re-enabled top-k/p samplers for new implementation		2025-04-19 14:04:34 -05:00
..
emb	added some more notes, tweaks (RIP DAC, it's over)	2025-04-17 20:24:40 -05:00
engines	cannot get segmented mask to actually work without gradients exploding (need to find a different way to do duration prediction...)	2025-03-27 00:51:41 -05:00
models	more notes / re-enabled top-k/p samplers for new implementation	2025-04-19 14:04:34 -05:00
utils	cannot get segmented mask to actually work without gradients exploding (need to find a different way to do duration prediction...)	2025-03-27 00:51:41 -05:00
__init__.py	nothing could go wrong part 2 (reverted and rewrote commits since there was a nasty regression)	2025-03-25 23:06:16 -05:00
__main__.py	nothing could go wrong part 2 (reverted and rewrote commits since there was a nasty regression)	2025-03-25 23:06:16 -05:00
config.py	more settings bloat because there seems to be instability with the encoder as-is	2025-04-12 12:53:44 -05:00
data.py	added some more notes, tweaks (RIP DAC, it's over)	2025-04-17 20:24:40 -05:00
demo.py	ugh	2025-02-28 01:06:38 -06:00
export.py	updated vall_e.cpp, but i could have sworn it worked much better than this......	2025-04-05 01:22:51 -05:00
inference.py	should not be working late	2025-04-03 23:32:58 -05:00
metrics.py
plot.py
samplers.py
train.py	the culprit was initializing the level_weights for killing newly trained models.............	2025-04-10 23:06:16 -05:00
webui.py	new implementation tweaks and fixes to make it actually better (there were a lot of badwrong things being done that harmed the output quality, will evaluate the model further)	2025-04-18 20:36:44 -05:00