11 Commits

Author	SHA1	Message	Date
Your Name	1210025d8b	fix flake8	2025-04-29 20:34:12 -07:00
yfyeung	26c022665b	remove space if existing ... fix	2025-04-29 10:43:10 -07:00
yfyeung	d1c336f589	remove ineffective normalize_text_alimeeting	2025-04-29 10:43:10 -07:00
yfyeung	26aef4a926	remove ineffective normalize_text_alimeeting	2025-04-29 10:43:10 -07:00
yfyeung	46b9be31cc	remove batch shaving	2025-04-29 10:43:10 -07:00
yfyeung	f5d2aa1f5d	fix train/eval mode ... reformat reformat fix	2025-04-29 10:43:08 -07:00
Your Name	3511b7db12	fix train.py and decode.py ... fix	2025-04-23 09:34:22 -07:00
Fangjun Kuang	d4d4f281ec	Revert "Replace deprecated pytorch methods (#1814)" (#1841) ... This reverts commit 3e4da5f78160d3dba3bdf97968bd7ceb8c11631f.	2024-12-18 16:49:57 +08:00
Li Peng	3e4da5f781	Replace deprecated pytorch methods (#1814) ... * Replace deprecated pytorch methods - torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...) - torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...) * Replace `with autocast(...)` with `with autocast("cuda", ...)` Co-authored-by: Li Peng <lipeng@unisound.ai>	2024-12-16 10:24:16 +08:00
zr_jin	88bacfb9e6	minor fixes for the repo (#1775) ... * minor fixes for the repo Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>	2024-10-21 13:51:56 +08:00
Yuekai Zhang	890eeec82c	Add qwen-audio style model training: using whisper + qwen2 (#1652)	2024-06-16 12:14:44 +08:00