42 Commits

Author	SHA1	Message	Date
root	e65725810c	fix mmsu	2025-05-13 09:13:12 +00:00
root	cbf3af31fd	add voicebench eval	2025-05-13 05:37:11 +00:00
root	89781b9bb1	add cosyvoice2 decode	2025-05-12 10:06:59 +00:00
root	b20a0d0e35	add on the fly feature	2025-05-08 19:21:41 -07:00
root	bd2df570ad	add debug script	2025-05-08 03:37:26 -07:00
root	37db65984c	remove k2 dependency	2025-05-08 03:02:34 -07:00
root	e41c1cabd5	add dependency	2025-05-08 07:56:14 +00:00
root	7cc366d82d	add en data, cosy2 token for training	2025-05-08 07:23:22 +00:00
root	2dd40b62ef	add vocalnet en data	2025-05-08 06:29:46 +00:00
root	08be51a91f	change pic	2025-04-29 10:09:57 +00:00
root	11bd3c9ad8	lint	2025-04-29 09:46:44 +00:00
root	360f0aa397	update README	2025-04-29 08:49:12 +00:00
root	448a4eeea7	update hf dataset loading into lhotse	2025-04-29 07:33:34 +00:00
Yuekai Zhang	d742043e75	refactor decode part	2025-04-25 18:31:43 +08:00
root	71a0a442a6	add history cache	2025-04-25 10:05:07 +00:00
Yuekai Zhang	47920c2336	add gradio demo	2025-04-25 16:05:37 +08:00
Yuekai Zhang	72addd40f5	change place	2025-04-25 14:22:16 +08:00
Yuekai Zhang	9a07363a8d	remove unsed	2025-04-25 14:21:50 +08:00
Yuekai Zhang	6ea7ec8543	remove offline tab	2025-04-25 14:10:30 +08:00
Yuekai Zhang	6955639d22	add qwen omni web demo	2025-04-25 14:08:25 +08:00
root	3642dfd8c3	refactor code	2025-04-25 05:36:18 +00:00
root	2e9be46703	debug	2025-04-24 08:24:11 +00:00
root	478d56efd8	fix bugs when padding right	2025-04-23 07:33:27 +00:00
Yuekai Zhang	23fdef2fd3	add codec decode	2025-04-21 17:57:57 +08:00
Yuekai Zhang	09d81b44a7	change padding side name	2025-04-21 17:10:25 +08:00
Yuekai Zhang	7db40052d6	add flash attn support	2025-04-21 14:54:28 +08:00
root	b305cdacc0	fix padding side	2025-04-21 06:23:10 +00:00
root	bdb60f6ddc	add codec lm	2025-04-21 01:00:06 +00:00
root	458d697acc	fix batch_size>1 decoding bug	2025-04-15 13:41:33 +00:00
root	0c02da82ac	refine decoding method	2025-04-15 06:53:20 +00:00
root	3ad075af60	s2t training	2025-04-15 02:16:03 +00:00
Yuekai Zhang	1d11662016	fix multi rounds data	2025-04-14 14:32:42 +08:00
root	202d764cfb	remove text norm	2025-04-14 05:35:07 +00:00
root	6b69276b19	add training stage	2025-04-11 06:51:51 +00:00
root	e6897b10fa	make asr decode results align	2025-04-11 06:51:51 +00:00
root	cca562d538	migrate from speech llm	2025-04-11 06:51:50 +00:00
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	ebbd396c2b	update multi-hans-zh whisper-qwen-7b results (#1677) ... * update qwen-7b whisper encoder results * update qwen-7b whisper encoder results * fix typo	2024-07-03 19:55:12 +08:00
Yuekai Zhang	ff2bef9e50	update multi-hans whisper-qwen-1.5b results (#1657)	2024-06-19 11:10:31 +08:00
Yuekai Zhang	890eeec82c	Add qwen-audio style model training: using whisper + qwen2 (#1652)	2024-06-16 12:14:44 +08:00