mrq 09cda7d3f9 added sampling by speaker group name (might be better to de-emphasize the LibriVox/Audiobooks that are in large numbers, and emphasize the smaller pools), log cleanup		2023-10-16 19:30:38 -05:00
..
__init__.py	tweaks to try and get deepspeed quantized inferencing, validating bitsandbytes and deepspeed quantization, nothing seems to work	2023-10-12 22:21:43 -05:00
adaln.py
ar_nar.py	added sampling by speaker group name (might be better to de-emphasize the LibriVox/Audiobooks that are in large numbers, and emphasize the smaller pools), log cleanup	2023-10-16 19:30:38 -05:00
ar.py	actually use langs from the dataloader	2023-10-11 21:21:50 -05:00
base.py	mucked around with the loss calculation, this seems better?	2023-10-13 18:22:21 -05:00
nar.py	actually use langs from the dataloader	2023-10-11 21:21:50 -05:00
retnet.py
transformer.py