mrq 93feb5660f do not like that		2025-02-27 23:59:56 -06:00
..
emb
engines	I think I made resp_parallel_training=True faster with loss factoring?	2025-02-26 23:13:32 -06:00
models	do not like that	2025-02-27 23:59:56 -06:00
utils	when you already had these ideas to stabilize training but you just ignored them	2025-02-27 23:39:20 -06:00
__init__.py
__main__.py
config.py	when you already had these ideas to stabilize training but you just ignored them	2025-02-27 23:39:20 -06:00
data.py	require minimum of 1 second durations for training because of my slop code auto-transposing that I don't wanna fix right now	2025-02-26 22:00:33 -06:00
demo.py
export.py
inference.py	segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)	2025-02-26 21:26:13 -06:00
metrics.py
plot.py
samplers.py
train.py	require minimum of 1 second durations for training because of my slop code auto-transposing that I don't wanna fix right now	2025-02-26 22:00:33 -06:00
webui.py