mrq 2fd82a7a22 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	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
base.py	one more time one more time (this normalization isn't a spook)	2025-03-07 19:32:42 -06:00
deepspeed.py	stuff for interfacing with the loss scaler value (because I want to cap it)	2025-03-06 17:07:29 -06:00