mrq d53038a9e4 actually have split classifiers working		2024-07-19 15:33:31 -05:00
..
emb	fixes...	2024-07-18 23:25:32 -05:00
engines	actually have split classifiers working	2024-07-19 15:33:31 -05:00
ext	fixes	2024-06-04 00:07:00 -05:00
models	actually have split classifiers working	2024-07-19 15:33:31 -05:00
utils	oops, kept forgetting to actually pass in lang/tone tokens (despite not really using these at the moment)	2024-07-18 14:18:34 -05:00
__init__.py
__main__.py	sanity cleanup: moved experimental features under its own thing	2024-06-30 10:37:33 -05:00
config.py	actually have split classifiers working	2024-07-19 15:33:31 -05:00
data.py	fixes...	2024-07-18 23:25:32 -05:00
export.py	mechanism to store the model config inside the weights and load them, some other things to allow LoRA training on the RetNet (gradient checkpointing will gripe about inputs not having require_grad and nothing seems to remedy it)	2024-07-16 18:23:13 -05:00
inference.py	allow loading a different model within the web ui (apparently I did not have the web UI in the documentation)	2024-07-15 19:59:48 -05:00
plot.py	ugh	2024-06-09 11:39:43 -05:00
samplers.py	actually have split classifiers working	2024-07-19 15:33:31 -05:00
train.py	eval/validation fix for SpeechX tasks	2024-07-19 09:16:37 -05:00
webui.py	allow loading a different model within the web ui (apparently I did not have the web UI in the documentation)	2024-07-15 19:59:48 -05:00