mrq 497bdfc67b more work (the wall is non-causal decoding......)		2024-12-22 20:11:31 -06:00
..
cleanup_dataset.py	re-adapted process_libritts.py to a 'better' way (better because it processed without needing to shuffle a bunch of things and adapt to cope or something)	2024-08-05 20:34:58 -05:00
deduplicate_librilight_libritts.py	re-adapted process_libritts.py to a 'better' way (better because it processed without needing to shuffle a bunch of things and adapt to cope or something)	2024-08-05 20:34:58 -05:00
hf_test.py	more work (the wall is non-causal decoding......)	2024-12-22 20:11:31 -06:00
parse_ppp.py	re-adapted process_libritts.py to a 'better' way (better because it processed without needing to shuffle a bunch of things and adapt to cope or something)	2024-08-05 20:34:58 -05:00
prepare_librilight.py	re-adapted process_libritts.py to a 'better' way (better because it processed without needing to shuffle a bunch of things and adapt to cope or something)	2024-08-05 20:34:58 -05:00
process_emilia.py	fixes to process_emilia.py script	2024-12-09 14:38:09 -06:00
process_libritts.py	tweaks and things	2024-08-06 08:17:25 -05:00
process_nscripter.py	sanity checks (and I realized that the model actually had langs set to 4 in the yaml for KO/ZH so................	2024-12-19 19:08:57 -06:00
process_seed-tts.py	sanity checks (and I realized that the model actually had langs set to 4 in the yaml for KO/ZH so................	2024-12-19 19:08:57 -06:00
run.sh	nasty bandaid if there's no validation dataset specified during training (for example, during finetunes)	2023-08-30 18:23:05 -05:00
setup.sh	documentation update	2024-08-04 00:14:49 -05:00
train_tokenizer.py	re-adapted process_libritts.py to a 'better' way (better because it processed without needing to shuffle a bunch of things and adapt to cope or something)	2024-08-05 20:34:58 -05:00