mrq 6d42c9ae23 how foolish of me, not having a softmax as float32 (maybe addresses an emergent regression where bfloat16 training shits the bed where float16+loss scaling doesnt)		2025-04-07 22:51:52 -05:00
..
emb	ugh	2025-04-05 18:20:46 -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	how foolish of me, not having a softmax as float32 (maybe addresses an emergent regression where bfloat16 training shits the bed where float16+loss scaling doesnt)	2025-04-07 22:51:52 -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	ugh	2025-04-03 23:26:00 -05:00
data.py	reintroduced sampler_type = speaker because I think this might salvage the nemo model to have better speaker similarities	2025-04-03 19:01:10 -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	instead just compute a bunch of stuff on the transcriptions to store later in different names so I can just retrieve what I want, also added tongue twisters for nefarious reasons	2024-12-18 23:43:11 -06:00
plot.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00
samplers.py	agony	2025-02-12 00:18:24 -06:00
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