mrq b922f35b6b added documentation on how these new sampling parameters are very iffy and you really need to know what you are doing to use them because this is audio generation and not text generation		2023-09-08 20:43:36 -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 option to specify parameters to freeze per-model in YAML (because I need to see about committing atrocities with convering an AR into an AR+NAR)	2023-09-07 18:19:51 -05:00
models	added documentation on how these new sampling parameters are very iffy and you really need to know what you are doing to use them because this is audio generation and not text generation	2023-09-08 20:43:36 -05:00
utils	also cull frozen_params in the params optimizer receives to reduce VRAM it consumes	2023-09-07 18:27:02 -05:00
__init__.py
__main__.py	added lots of sampling options (top-k/top-p, repetition penalty, length penalty)	2023-09-08 20:30:54 -05:00
config.py	some day I'll get it right	2023-09-08 15:36:26 -05:00
data.py	added per-speaker samplers	2023-09-03 21:27:13 -05:00
export.py
inference.py	added lots of sampling options (top-k/top-p, repetition penalty, length penalty)	2023-09-08 20:30:54 -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	seems that my PromEmbedding/RespEmbedding doesn't actually work all that well, naively using dedicated MultiEmbeddings for AR/NAR in the monolithic model is the best way to go	2023-09-08 01:03:24 -05:00