25 Commits

Author	SHA1	Message	Date
lyuxiang.lx	66b80dbccb	online feature	2026-01-28 15:19:07 +00:00
lyuxiang.lx	1ceb2b7b1e	fix bug	2026-01-05 11:01:19 +08:00
lyuxiang.lx	4c19646b9a	update dataset	2025-12-29 12:46:34 +00:00
lyuxiang.lx	4d7295a9a7	fix cosyvoice3 training	2025-12-29 10:03:14 +00:00
lyuxiang.lx	ebef63066f	add instruct	2025-12-12 07:44:36 +00:00
lyuxiang.lx	63856565f3	update dpo	2025-06-24 11:49:20 +08:00
lyuxiang.lx	68100c267a	remove flow_cache	2025-05-23 16:07:27 +08:00
Xiang Lyu	88f467a8ac	Merge pull request #1232 from boji123/bj_dev_feat_len_pad ... a better solution for mismatch of speech feat len and speech token len when trainning	2025-04-30 09:41:50 +08:00
burkliu	038ff9f353	[feature] modify pad to trim	2025-04-25 10:36:25 +08:00
burkliu	65ad448714	[debug] a better solution for mismatch of speech feat len and speech token len, refer to https://github.com/FunAudioLLM/CosyVoice/issues/1051	2025-04-25 10:36:08 +08:00
ShengqiangLi	6d876f573c	feat: Support DPO	2025-04-16 14:57:35 +08:00
lyuxiang.lx	2a3e033ee1	fix lint	2025-02-07 16:23:03 +08:00
lyuxiang.lx	190840b8dc	fix pitch computation	2025-01-23 15:44:03 +08:00
lyuxiang.lx	1cfc5dd077	add online trt export	2025-01-10 13:55:05 +08:00
lyuxiang.lx	5ed5bb15c8	use stream read to save memory	2024-11-11 22:14:52 +08:00
lyuxiang.lx	29507bc77a	update lint	2024-10-16 13:06:31 +08:00
lyuxiang.lx	73784974ce	update hifigan	2024-10-16 12:15:49 +08:00
lyuxiang.lx	789ee9e5e7	add hifigan train	2024-10-16 11:37:32 +08:00
lyuxiang.lx	cb200b21c5	add hifigan train code	2024-10-09 17:36:42 +08:00
lyuxiang.lx	90433f5373	fix lint	2024-09-05 16:15:34 +08:00
lyuxiang.lx	6cebcb3410	move use_spk_embedding to processor	2024-07-11 13:15:34 +08:00
lyuxiang.lx	6a3e44242a	keep only embedding mean as spk embedding	2024-07-10 00:21:56 +08:00
lyuxiang.lx	7981796523	add WeTextProcessing	2024-07-09 23:37:54 +08:00
lyuxiang.lx	62c71075ac	update dockerfile	2024-07-08 16:40:46 +08:00
lyuxiang.lx	076829ab84	add cosyvoice code	2024-07-04 21:15:12 +08:00