mrq caad99ab78 fix for bsz>1 because I forgot the old implementation implicitly handles this		2025-04-02 17:17:37 -05:00
..
emb	ugh	2025-04-02 17:05:16 -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	fix for bsz>1 because I forgot the old implementation implicitly handles this	2025-04-02 17:17:37 -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
__main__.py
config.py	is this my last cope (falling back to explicit duration prediction, as this regression just won't go away) (also the smaller model was lobotomized because of my ROCm setup having a botched SDPA for who knows why)	2025-04-02 17:01:24 -05:00
data.py	re-added noise dataloader sampler whatever for the old implementation's other tasks that require it	2025-03-28 15:07:06 -05:00
demo.py
export.py
inference.py	is this my last cope (falling back to explicit duration prediction, as this regression just won't go away) (also the smaller model was lobotomized because of my ROCm setup having a botched SDPA for who knows why)	2025-04-02 17:01:24 -05:00
metrics.py
plot.py
samplers.py
train.py
webui.py