218 Commits

Author	SHA1	Message	Date
lyuxiang.lx	ebef63066f	add instruct	2025-12-12 07:44:36 +00:00
lyuxiang.lx	f21c4764ec	fix bug	2025-12-11 06:04:36 +00:00
lyuxiang.lx	927addadd8	fix lint	2025-12-10 02:17:00 +00:00
lyuxiang.lx	a051a09ba4	remove unncessary code	2025-12-09 15:41:02 +00:00
lyuxiang.lx	0c65d3c7ab	use automodel	2025-12-09 15:15:05 +00:00
lyuxiang.lx	56d9876037	fix bug	2025-12-09 07:57:10 +00:00
lyuxiang.lx	59f02cb85d	add vllm example	2025-12-08 11:14:12 +00:00
lyuxiang.lx	b4dd67a8af	add cosyvoice3 vllm example	2025-12-08 10:55:53 +00:00
lyuxiang.lx	bfa835a74b	add cosyvoice3 inference code	2025-12-08 10:04:11 +00:00
lyuxiang.lx	622a3a19b0	use wav file rather than tensor	2025-12-08 08:43:09 +00:00
lyuxiang.lx	f76f5abcc1	update	2025-08-22 14:42:34 +08:00
lyuxiang.lx	6b5eef62cc	update	2025-08-22 14:24:27 +08:00
lyuxiang.lx	dc96e4c984	update	2025-08-21 21:03:58 +08:00
lyuxiang.lx	70991d7327	update	2025-08-21 20:08:08 +08:00
lyuxiang.lx	8c96081f94	update	2025-08-21 11:45:36 +08:00
lyuxiang.lx	dd2d926147	update	2025-08-20 16:55:03 +08:00
lyuxiang.lx	da41f6175b	update	2025-08-19 18:53:18 +08:00
lyuxiang.lx	e3c2400abb	update	2025-08-19 16:23:59 +08:00
lyuxiang.lx	11515d0d5a	use bf16 for amp	2025-07-28 11:55:38 +08:00
lyuxiang.lx	b048a2d6db	fix dpo bug	2025-07-16 20:09:10 +08:00
lyuxiang.lx	8555549e88	fix lint	2025-07-07 14:52:12 +08:00
lyuxiang.lx	3047591fad	fix lint	2025-07-07 14:49:51 +08:00
lyuxiang.lx	35abb1f3b5	Merge branch 'main' of github.com:FunAudioLLM/CosyVoice into main	2025-07-07 10:56:06 +08:00
lyuxiang.lx	21a5efd8ae	fix lint	2025-06-29 13:21:44 +08:00
xxnuo	116c99bf39	Fix: remove overwrite_cache	2025-06-27 15:57:17 +08:00
xxnuo	6eaef42126	Fix: remove full_to_half	2025-06-27 15:55:00 +08:00
xxnuo	ff9694dc2c	Fix: Use wetext cache	2025-06-27 14:45:07 +08:00
xxnuo	4505924608	Fix: Use wetext replace WeTextProcessing	2025-06-27 14:43:57 +08:00
lyuxiang.lx	46dfe0439b	fix possible bug	2025-06-25 14:31:05 +08:00
lyuxiang.lx	63856565f3	update dpo	2025-06-24 11:49:20 +08:00
lyuxiang.lx	c939c80480	update	2025-06-01 08:46:47 +00:00
lyuxiang.lx	9b052a94c4	fix lint	2025-05-30 07:51:49 +00:00
lyuxiang.lx	6dd68b9d5e	add vllm inference	2025-05-30 07:22:35 +00:00
root	9f55c5af8f	add vllm export	2025-05-28 08:35:48 +00:00
lyuxiang.lx	cbfed4a9ee	send streaming as args	2025-05-27 13:47:12 +08:00
lyuxiang.lx	82219cdd27	update	2025-05-27 10:23:06 +08:00
lyuxiang.lx	3e12bb86bd	fix trt wrapper bug	2025-05-26 18:03:15 +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
bearlu	587604b2b4	fix inference_instruct2 speaker ID bug	2025-04-21 09:26:34 -07:00
lyuxiang.lx	e97cd1b655	fix cross_lingual bug	2025-04-19 09:08:47 +08:00
lyuxiang.lx	8d67d17f73	update	2025-04-16 20:18:49 +08:00
lyuxiang.lx	a442317d17	add flow trt wrapper	2025-04-16 17:57:02 +08:00
ShengqiangLi	6d876f573c	feat: Support DPO	2025-04-16 14:57:35 +08:00
lyuxiang.lx	3770c1c8b1	fix bug	2025-04-16 13:48:13 +08:00
lyuxiang.lx	2c193781cc	fix export_onnx.py	2025-04-15 17:29:42 +08:00
lyuxiang.lx	efe1d15960	fix export_onnx.py	2025-04-15 16:51:25 +08:00
lyuxiang.lx	9ebcf7b1ad	fix bug	2025-04-15 16:36:10 +08:00