51 Commits

Author	SHA1	Message	Date
lyuxiang.lx	68100c267a	remove flow_cache	2025-05-23 16:07:27 +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	a69b7e275d	fix vocoder train	2025-03-07 17:34:13 +08:00
lyuxiang.lx	2a3e033ee1	fix lint	2025-02-07 16:23:03 +08:00
lyuxiang.lx	1c062ab381	add flow decoder cache	2025-01-23 16:48:13 +08:00
lyuxiang.lx	190840b8dc	fix pitch computation	2025-01-23 15:44:03 +08:00
lyuxiang.lx	07e477519b	add llm bistream	2025-01-23 10:12:06 +08:00
lyuxiang.lx	43f9e9ab20	update	2025-01-13 10:30:13 +08:00
lyuxiang.lx	87475ccf41	fix conflict	2025-01-10 16:43:31 +08:00
lyuxiang.lx	1cfc5dd077	add online trt export	2025-01-10 13:55:05 +08:00
lyuxiang.lx	77d8cf13a3	update	2025-01-02 10:55:59 +08:00
lyuxiang.lx	b9ddcba5fd	add some instruction and assert	2024-12-30 16:41:57 +08:00
0xCAFEBABE0	b60c37b31a	fix(bug).when generating text that contains only punctuation marks or whitespace characters, the CPU usage reaches 100%, and the process crashes.	2024-12-30 10:48:43 +08:00
0xCAFEBABE0	bcc58cb4cb	Update common.py	2024-12-16 13:57:38 +08:00
0xCAFEBABE0	1d8d94de82	Update common.py	2024-12-16 13:56:28 +08:00
0xCAFEBABE0	0993ec5f08	Merge branch 'main' into bug_cpu_hang	2024-12-16 13:54:53 +08:00
lyuxiang.lx	ac70560364	fix lint	2024-12-16 09:54:24 +08:00
0xCAFEBABE0	84015697c2	fix(bug).when generating text that contains only punctuation marks or whitespace characters, the CPU usage reaches 100%, and the process crashes.	2024-12-12 16:49:39 +08:00
lyuxiang.lx	3e381002d7	add cosyvoice2	2024-12-11 16:14:19 +08:00
lyuxiang.lx	dc3f6432ba	fix bug	2024-11-22 15:11:55 +08:00
lyuxiang.lx	c3dfd23399	resume training	2024-11-15 16:41:17 +08:00
lyuxiang.lx	0930b4a106	fix lint	2024-10-22 11:22:35 +08:00
lyuxiang.lx	d554db7e32	fix hifigan init bug	2024-10-22 11:20:47 +08:00
lyuxiang.lx	5bd5dfecab	remove unnecessary f0 loss in discrimnator	2024-10-18 15:58:19 +08:00
lyuxiang.lx	29507bc77a	update lint	2024-10-16 13:06:31 +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
zhuyunfeng	0b76dfa1eb	Update frontend_utils.py ... Fix typo	2024-09-29 14:41:33 +08:00
zhuyunfeng	74a449ad1f	Update frontend_utils.py ... Fix typo	2024-09-29 14:26:33 +08:00
zhuyunfeng	9c0aa1918b	Update frontend_utils.py ... "Fix the bug in `split_paragraph` where the last sentence of synthesized text with multiple paragraphs loses punctuation, causing it to be lost."	2024-09-29 14:19:31 +08:00
lyuxiang.lx	72b89a52fb	update vc/tts code	2024-09-26 11:53:10 +08:00
lyuxiang.lx	49015f63e6	add vc code	2024-09-26 10:49:22 +08:00
lyuxiang.lx	f65eca6723	add speech fade in out	2024-09-19 18:02:42 +08:00
Xiang Lyu	cd26f11859	Merge pull request #379 from boji123/bj_dev_stream_fix ... [debug] fix badcase, add fade on speech output	2024-09-19 17:32:04 +08:00
lyuxiang.lx	e19e80fcd8	update tempo change	2024-09-18 16:13:40 +08:00
liubaiji	df653f1e98	[refator] modify fade_in_out func to a commom form	2024-09-11 10:36:32 +08:00
lyuxiang.lx	90433f5373	fix lint	2024-09-05 16:15:34 +08:00
lyuxiang.lx	1d881df8b2	fix vocoder speech overlap	2024-08-29 19:10:08 +08:00
lyuxiang.lx	f4e70e222c	update stream code	2024-08-07 17:09:23 +08:00
lyuxiang.lx	a13411c561	add stream code	2024-07-23 00:02:30 +08:00
刘悦	f2939a9a50	Update file_utils.py ... fix flake8	2024-07-22 16:02:18 +08:00
刘悦	cf43100f66	Update file_utils.py ... add speed_change function	2024-07-22 11:44:39 +08:00
lyuxiang.lx	6cebcb3410	move use_spk_embedding to processor	2024-07-11 13:15:34 +08:00
lyuxiang.lx	0fd15bb12b	use spk_embedding when sft	2024-07-10 17:49:32 +08:00
lyuxiang.lx	793a24862c	add constant lr scheduler	2024-07-10 16:37:25 +08:00
passerbya	69026d83bb	没有标点结尾时默认加上句号	2024-07-09 17:42:40 +08:00
passerbya	f9fe31f200	文本中没有标点时无法合成	2024-07-09 17:26:19 +08:00
passerbya	2f496104ec	半角句号会导致合成失败：RuntimeError: torch.cat(): expected a non-empty list of Tensors ... text='小明因为感冒,鼻子不通,讲话总带着齉音.' File "/usr/local/data/CosyVoice/cosyvoice/cli/cosyvoice.py", line 62, in inference_zero_shot return {'tts_speech': torch.concat(tts_speeches, dim=1)} RuntimeError: torch.cat(): expected a non-empty list of Tensors 原因为self.frontend.text_normalize(tts_text, split=True)返回为空	2024-07-09 08:17:34 +08:00
lyuxiang.lx	71238461f0	remove academic and change to iic/CosyVoice_ttsfrd	2024-07-07 12:19:34 +08:00