mrq a6bfe43590 added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model)		2023-09-18 18:55:41 -05:00
..
emb	(need to verify) added modifying model size and config bool to align with VALL-E continuous' methodology	2023-09-01 17:19:34 -05:00
engines	added light web UI (need to port the telemetry disabling bandaids from aivc)	2023-09-09 16:17:20 -05:00
models	added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model)	2023-09-18 18:55:41 -05:00
utils	added light web UI (need to port the telemetry disabling bandaids from aivc)	2023-09-09 16:17:20 -05:00
__init__.py	Rewrite init	2023-08-02 21:53:35 +00:00
__main__.py	added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model)	2023-09-18 18:55:41 -05:00
config.py	unified more things with training the AR+NAR monolothic model	2023-09-12 15:54:41 -05:00
data.py	added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model)	2023-09-18 18:55:41 -05:00
export.py	ops	2023-08-20 13:42:18 -05:00
inference.py	added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model)	2023-09-18 18:55:41 -05:00
plot.py	integrated plot script, added tts-c task token to help the model be able to mix between normal VALL-E and VALL-E continuous	2023-09-02 16:29:53 -05:00
train.py	have loss for the NAR not-ignore the text prompt, I imagine this should help the NAR and explain why it's always had a bit of an issue with training	2023-09-15 19:08:44 -05:00
webui.py	added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model)	2023-09-18 18:55:41 -05:00