mrq 90b3509404 I'll just cope and say I cannot apply segmented attention masks to the smaller model as it's too trained on not doing it, and the regression came from dumb python aliasing rules		2025-03-27 13:27:51 -05:00
..
emb
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	I'll just cope and say I cannot apply segmented attention masks to the smaller model as it's too trained on not doing it, and the regression came from dumb python aliasing rules	2025-03-27 13:27:51 -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	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
data.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
demo.py
export.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
inference.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
metrics.py
plot.py
samplers.py
train.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
webui.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