361 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
lyuxiang.lx	cbfed4a9ee	send streaming as args	2025-05-27 13:47:12 +08:00
lyuxiang.lx	54d21b40f0	update	2025-05-27 10:40:45 +08:00
lyuxiang.lx	c3250c222f	add trt_concurrent arg	2025-05-27 10:34:59 +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
lyuxiang.lx	7f8bea2669	Merge branch 'dev/lyuxiang.lx' of github.com:FunAudioLLM/CosyVoice into dev/lyuxiang.lx	2025-04-16 15:00:24 +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
lyuxiang.lx	37e48dd318	optimize vc code	2025-04-15 16:15:20 +08:00
lyuxiang.lx	c07cd3d730	fix lint	2025-04-15 15:00:29 +08:00
lyuxiang.lx	36aec2c0f7	optimize flow cache code	2025-04-15 13:58:52 +08:00
lyuxiang.lx	d71d790f55	fix flow cache bug	2025-04-15 13:12:25 +08:00
lyuxiang.lx	e1ffb1e978	fix lint	2025-04-15 11:46:53 +08:00
lyuxiang.lx	9fea0f0836	add_zero_shot_spk	2025-04-15 11:45:00 +08:00
lyuxiang.lx	9dc559fc2a	force set use_flow_cache	2025-04-08 12:23:26 +08:00
Xiang Lyu	634edfadf0	Merge pull request #983 from Shengqiang-Li/main ... feat: Support DPO	2025-04-08 12:14:51 +08:00
Xiang Lyu	b56dfa223d	Merge pull request #1140 from FunAudioLLM/dev/lyuxiang.lx ... Dev/lyuxiang.lx	2025-04-07 23:04:37 +08:00
lyuxiang.lx	f0b8e892f6	fix lint	2025-04-07 23:04:01 +08:00
lyuxiang.lx	cfc68f379c	only keep online export	2025-04-07 22:54:13 +08:00
lyuxiang.lx	4951d2ad1a	update	2025-04-07 22:45:47 +08:00
lyuxiang.lx	d9ffd592f6	use static_chunk_size in flow training	2025-04-07 22:34:45 +08:00
lyuxiang.lx	7902d1c17f	set use_flow_cache=True when export	2025-04-07 22:27:17 +08:00
lyuxiang.lx	39ffc50dec	add flow cache inference code	2025-04-07 21:23:09 +08:00
Xiang Lyu	08312f4c46	Merge pull request #1100 from jingfelix/fix/dockerfile-dependency ... fix: missing dependency in `runtime/python/Dockerfile`	2025-03-25 08:30:26 +08:00
jingfelix	c6d8737336	fix: missing dependency in runtime/python/Dockerfile ... Signed-off-by: jingfelix <jingfelix@outlook.com>	2025-03-22 23:34:59 +08:00
ShengqiangLi	a22873e360	feat: Support DPO	2025-03-16 18:33:42 +08:00
Xiang Lyu	c97b445df4	Merge pull request #1036 from hwangsihu/main ... Fixed an issue where onnxruntime would not install on Windows	2025-03-10 15:48:04 +08:00
hwangsihu	265507f213	Fixed an issue where onnxruntime would not install on Windows	2025-03-10 16:07:01 +09:00
lyuxiang.lx	a69b7e275d	fix vocoder train	2025-03-07 17:34:13 +08:00
lyuxiang.lx	fcc054f64e	fix hifigan bug	2025-02-18 14:45:43 +08:00
Xiang Lyu	fd45708e4b	Merge pull request #977 from hanasay/main ... Convert audio to mono while extract speech token	2025-02-16 12:51:04 +08:00
hanasay	296ed4f526	Convert audio to mono while extract speech token ... modified： tools/extract_speech_token.py	2025-02-14 15:25:45 +08:00
lyuxiang.lx	890300513c	fix bug	2025-02-11 15:56:20 +08:00
lyuxiang.lx	f77c6a85aa	fix bug	2025-02-11 00:07:12 +08:00
lyuxiang.lx	b6d66ce2e3	update	2025-02-08 13:58:41 +08:00
lyuxiang.lx	8e4f252d32	add llm bistream	2025-02-08 12:15:37 +08:00
lyuxiang.lx	79b7dff8d2	add llm train	2025-02-07 17:17:12 +08:00
Xiang Lyu	95e99e0417	Merge pull request #940 from c4fun/fastapi-cosyvoice2 ... Add a inference_instruct2 route to support and defaultly supports cosyvoice2 in fastapi server	2025-02-07 16:30:27 +08:00
c4fun	ba6d8c07ba	revert the main function to original and only preserve the inference endpoint	2025-02-07 16:28:30 +08:00