deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity
196 Commits 5 Branches 2 Tags
1e853ed0801a301ddd02fe63981fcfb217d9d10a
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Xiang Lyu 07352a50b3 Merge pull request #670 from FunAudioLLM/dev/lyuxiang.lx 
fix bug
 2024-11-22 15:12:50 +08:00
lyuxiang.lx dc3f6432ba fix bug 2024-11-22 15:11:55 +08:00
Xiang Lyu d6dbdfbf31 Merge pull request #653 from FunAudioLLM/dev/lyuxiang.lx 
resume training
 2024-11-15 16:43:44 +08:00
lyuxiang.lx c3dfd23399 resume training 2024-11-15 16:41:17 +08:00
Xiang Lyu 7701325969 Merge pull request #639 from FunAudioLLM/dev/lyuxiang.lx 
use stream read to save memory
 2024-11-11 22:17:21 +08:00
lyuxiang.lx 5ed5bb15c8 use stream read to save memory 2024-11-11 22:14:52 +08:00
Xiang Lyu 6d22d0b76f Merge pull request #618 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-11-05 09:36:51 +08:00
lyuxiang.lx 487701c98c fix huggingface-hub version 2024-11-05 09:34:51 +08:00
Xiang Lyu 3914b54c82 Merge pull request #603 from oongrider/f_free_cache_dict 
release flow_cache_dict to prevent potential memory leaks in long-running processes
 2024-11-04 11:18:17 +08:00
lyuxiang.lx a2ece33477 fix hifigan yaml bug 2024-11-01 16:17:01 +08:00
Xiang Lyu dfcd6d0a64 Merge pull request #504 from liutaocode/patch-1 
Update model.py
 2024-10-22 13:54:01 +08:00
lyuxiang.lx 16d66dc6a6 fix short tts_text bug 2024-10-22 12:56:29 +08:00
Xiang Lyu d8f00f4793 Merge pull request #580 from FunAudioLLM/dev/lyuxiang.lx 
fix hifigan init bug
 2024-10-22 11:23:32 +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
Xiang Lyu 027e1ccb82 Merge pull request #511 from FunAudioLLM/dev/lyuxiang.lx 
remove unnecessary f0 loss in discrimnator
 2024-10-18 16:03:15 +08:00
lyuxiang.lx d1f7c1c9d7 remove unnecessary code 2024-10-18 16:00:14 +08:00
lyuxiang.lx 5bd5dfecab remove unnecessary f0 loss in discrimnator 2024-10-18 15:58:19 +08:00
Xiang Lyu 0f19b97c5a Merge pull request #497 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-10-16 15:35:27 +08:00
lyuxiang.lx a4db3db8ed update flow cache 2024-10-16 15:24:47 +08:00
Xiang Lyu ace734def8 Merge pull request #455 from boji123/bj_dev_stream_fix_promptcache 
[debug] support flow cache, for sharper tts_mel output (handle prompt bug)
 2024-10-16 14:12:40 +08:00
Xiang Lyu 5157baf166 Merge pull request #496 from FunAudioLLM/dev/lyuxiang.lx 
fix typo
 2024-10-16 13:58:08 +08:00
lyuxiang.lx 6b7286eb62 fix typo 2024-10-16 13:57:27 +08:00
Xiang Lyu 21ddaeccf2 Merge pull request #495 from FunAudioLLM/dev/lyuxiang.lx 
fix bug
 2024-10-16 13:31:15 +08:00
lyuxiang.lx 7e6d60c24c fix bug 2024-10-16 13:30:13 +08:00
Xiang Lyu de76577a9f Merge pull request #494 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-10-16 13:07:25 +08:00
lyuxiang.lx 29507bc77a update lint 2024-10-16 13:06:31 +08:00
lyuxiang.lx 555efd0301 update readme 2024-10-16 12:59:57 +08:00
lyuxiang.lx ea7d709fbb update hifigan 2024-10-16 12:43:55 +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
Xiang Lyu d49259855b Merge pull request #453 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-09-29 14:54:31 +08:00
Xiang Lyu 67f298d94a Merge pull request #451 from zhuzizyf/bug-fix-split_paragraph 
Bug fix for split_paragraph
 2024-09-29 14:51:18 +08:00
Xiang Lyu 4a1ec98304 Merge pull request #450 from zhuzizyf/optimize-TN 
Optimize TN processing
 2024-09-29 14:49:32 +08:00
lyuxiang.lx abc6f70ace update 25hz yaml 2024-09-29 10:42:57 +08:00
lyuxiang.lx ffa28e3bbd update token args 2024-09-29 10:35:10 +08:00
lyuxiang.lx 8555ab4ded update readme 2024-09-26 15:02:27 +08:00
Xiang Lyu 69202008ce Merge pull request #436 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-09-26 15:00:22 +08:00
lyuxiang.lx ba3d9693da load jit to device 2024-09-26 14:55:03 +08:00
lyuxiang.lx 06934c38c7 update vc code 2024-09-26 14:46:24 +08:00
lyuxiang.lx d52358f6c5 update readme 2024-09-26 12:10:52 +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 ed87445540 add 25hz text tokenizer 2024-09-25 11:24:02 +08:00
Xiang Lyu f6d44af146 Merge pull request #424 from zhoupc2015/main 
fastapi服务启动限制ip从127.0.0.1改为0.0.0.0，这样docker映射端口才可以使用
 2024-09-23 16:06:30 +08:00
Xiang Lyu 95051e5761 Merge pull request #408 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-09-19 18:07:11 +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
Xiang Lyu 28f1353324 Merge pull request #404 from FunAudioLLM/dev/lyuxiang.lx 
Dev/lyuxiang.lx
 2024-09-18 17:43:45 +08:00
lyuxiang.lx f6b5c42823 fix flake 2024-09-18 17:42:54 +08:00
lyuxiang.lx ff8e63567a use thread pool in tools 2024-09-18 17:41:15 +08:00
Xiang Lyu 2665b06e95 Merge pull request #356 from MiXaiLL76/main 
Implemented fast processing of extract_embedding
 2024-09-18 16:16:46 +08:00
Xiang Lyu 2898d5a851 Merge pull request #403 from FunAudioLLM/dev/lyuxiang.lx 
update tempo change
 2024-09-18 16:14:40 +08:00
lyuxiang.lx e19e80fcd8 update tempo change 2024-09-18 16:13:40 +08:00
Xiang Lyu f517d3627a Merge pull request #378 from dongwon00kim/docker 
Add dockerfile for python 3.8, cuda 11.8 and torch 2.0.1 version
 2024-09-18 11:51:57 +08:00
Xiang Lyu c901a12789 Merge pull request #360 from FunAudioLLM/dev/lyuxiang.lx 
set onnx to false as last chunk rtf unstable
 2024-09-06 17:12:23 +08:00
lyuxiang.lx 122df8c420 set onnx to false as last chunk rtf unstable 2024-09-06 17:10:54 +08:00
lyuxiang.lx bcda6d807c add prompt contraint 2024-09-05 17:09:07 +08:00
lyuxiang.lx 4d6a55243c update workflow 2024-09-05 16:25:25 +08:00
Xiang Lyu 33a585374a Merge pull request #354 from FunAudioLLM/dev/lyuxiang.lx 
fix readme
 2024-09-05 16:16:42 +08:00
lyuxiang.lx 90433f5373 fix lint 2024-09-05 16:15:34 +08:00
lyuxiang.lx eeebc45313 fix readme 2024-09-05 14:39:42 +08:00
lyuxiang.lx 9100813b79 add lint workflow 2024-09-05 14:37:21 +08:00
Xiang Lyu 7f5e391041 Merge pull request #353 from FunAudioLLM/inference_streaming 
onnx and fastapi
 2024-09-05 14:28:16 +08:00
lyuxiang.lx e141634da1 remove unnecessary code 2024-09-05 14:26:12 +08:00
lyuxiang.lx 11eacb810e add uvicorn requirements 2024-09-05 14:12:27 +08:00
lyuxiang.lx 7555afb90a update fastapi 2024-09-05 14:09:40 +08:00
lyuxiang.lx 2ce724045b add onnx export 2024-09-04 18:15:33 +08:00
lyuxiang.lx 7795445ed9 update roadmap 2024-09-04 16:36:18 +08:00
Xiang Lyu d8197de4cc Merge pull request #347 from hexisyztem/inference_streaming 
export onnx
 2024-09-03 11:25:15 +08:00
Xiang Lyu d2dea3d928 Merge pull request #330 from hexisyztem/flow_tensorrt 
Flow tensorrt
 2024-08-30 14:20:25 +08:00
Xiang Lyu ee988420f3 Merge branch 'inference_streaming' into flow_tensorrt 2024-08-30 14:20:06 +08:00
Xiang Lyu 20e0715dac Merge pull request #327 from FunAudioLLM/inference_streaming 
Inference streaming
 2024-08-29 23:51:21 +08:00
Xiang Lyu 662012999a Merge branch 'main' into inference_streaming 2024-08-29 23:48:02 +08:00
lyuxiang.lx 1ab3186799 revert trt TODO 2024-08-29 23:35:19 +08:00
lyuxiang.lx 1d881df8b2 fix vocoder speech overlap 2024-08-29 19:10:08 +08:00
lyuxiang.lx f1e374a9bb add trt script TODO 2024-08-29 10:44:04 +08:00
lyuxiang.lx 8b097f7625 add export script 2024-08-28 19:37:35 +08:00
Xiang Lyu dcc943db43 Merge pull request #323 from FunAudioLLM/hengwu.zty/zh_example 
change dropout_rate to float type
 2024-08-28 19:00:45 +08:00
lyuxiang.lx 9ab298dd49 add llm export script 2024-08-28 18:21:11 +08:00
Xiang Lyu bb690d9d1e Merge pull request #293 from FunAudioLLM/hengwu.zty/zh_example 
add chinese example
 2024-08-19 10:04:31 +08:00
Xiang Lyu 43a5f9cc58 Merge pull request #265 from eltociear/patch-2 
chore: update encoder.py
 2024-08-10 21:38:53 +08:00
lyuxiang.lx f4e70e222c update stream code 2024-08-07 17:09:23 +08:00
lyuxiang.lx 6be8d0fc36 add server_name 2024-08-01 15:33:56 +08:00
lyuxiang.lx 9504c3f88b fix flow matching training for zero shot inference 2024-08-01 10:54:27 +08:00
lyuxiang.lx 553244b8f2 add roadmap 2024-07-30 13:51:20 +08:00
lyuxiang.lx 02f941d348 update model inference 2024-07-24 19:18:09 +08:00
lyuxiang.lx a13411c561 add stream code 2024-07-23 00:02:30 +08:00
Xiang Lyu 2895d99b9a Merge pull request #182 from v3ucn/speed_change_sox_version 
Speed change sox version
 2024-07-22 16:11:43 +08:00
lyuxiang.lx ead9644e86 change flow config in cosyvoice.fromscratch.yaml 2024-07-18 11:18:45 +08:00
Xiang Lyu 47dec8d2bc Merge pull request #127 from Cxywzx/main 
FIX: 修复下载解压完成LibriTTS数据时，生成.complete文件失败。
 2024-07-15 10:06:04 +08:00
Xiang Lyu 51c21660f3 Merge pull request #133 from zhuzizyf/fix-frontend-bug 
Update frontend.py
 2024-07-15 10:01:51 +08:00
Xiang Lyu d1df60590a Merge pull request #106 from v3ucn/corss 
接口服务允许跨域请求，接入其他服务，比如ollama或者其他大模型服务
 2024-07-12 10:03:44 +08:00
lyuxiang.lx c2f9254006 add fastapi usage 2024-07-11 17:47:48 +08:00
lyuxiang.lx 44aea805ea add train cfg in flow matching 2024-07-11 17:36:59 +08:00
Xiang Lyu c7d9754eee Merge pull request #56 from iflamed/fastapi 
Add Fastapi server to serve TTS and download script
 2024-07-11 15:21:49 +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 a723ea375e Merge branch 'main' of github.com:FunAudioLLM/CosyVoice into main 2024-07-10 16:42:11 +08:00