Commit Graph

50 Commits

Author SHA1 Message Date
babysor00
45bc43bf3c Add description of new vocoder and pretrained models 2021-09-08 23:36:35 +08:00
Vega
dacedfa9cc
Merge pull request #76 from PeijiYang/main
Support "hifigan vocoder" for realtime synthesis
2021-09-08 23:06:14 +08:00
peijiyang
b60b75ea89 remove hardcode and unused part 2021-09-08 11:17:20 +08:00
peijiyang
c4a8c72b83 add pretrained hifigan 2021-09-07 21:50:31 +08:00
peijiyang
8195a55a25 add hifigan vocoder 2021-09-07 21:41:16 +08:00
Nemo
024d88ae96 Ignore vocoder models except pretrained 2021-09-01 08:44:43 +08:00
babysor00
5c0cb50c3e Add quick path to preprocess audio, denoise audio when loading in toolbox 2021-08-30 22:22:06 +08:00
babysor00
2f1f4f70b4 add support of aishell, magic data in toolbox 2021-08-29 16:31:40 +08:00
babysor00
4132bd113f Add readme instruction to train vocoder 2021-08-29 15:48:11 +08:00
babysor00
5950eea895 Support training your own vocoder 2021-08-29 15:43:54 +08:00
babysor00
630023c7b2 format readme and add paper references 2021-08-29 10:55:59 +08:00
babysor00
17d47589c1 Fix compatibility issue of symbols 2021-08-29 00:48:07 +08:00
Nemo
0bba0a806e
Update README.md 2021-08-28 19:56:19 +08:00
Nemo
331e1d4238
Update README-CN.md 2021-08-28 19:55:42 +08:00
Vega
2130908449
Add newbie friendly version 2021-08-28 09:40:44 +08:00
Nemo
95bbcf6cd8 Add readme to support aishell3 2021-08-25 23:14:30 +08:00
Nemo
a6f8c8a39a Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main 2021-08-25 23:11:34 +08:00
Nemo
0cc3f569fa [dataset]support aishell3(tested) 2021-08-25 23:11:29 +08:00
Vega
c3fb378b63
Update README-CN.md 2021-08-24 00:03:13 +08:00
Vega
9f30ca8e92
Merge pull request #38 from XiuChen-Liu/main
更新 README
2021-08-23 16:48:41 +08:00
XiuChen-Liu
0ede0ad771 UPDATE README.md 2021-08-23 15:37:33 +08:00
XiuChen-Liu
16c1d2049f UPDATE README-CN.md 2021-08-23 15:37:16 +08:00
Vega
a810e6a472
Merge pull request #32 from Nthily/main
更新 README
2021-08-23 13:14:38 +08:00
Nthily
4f23833a69
Update README.md 2021-08-23 03:17:32 +02:00
Nthily
e25072a4a8
Update README-CN.md 2021-08-23 03:16:35 +02:00
Nthily
289ededebc
Update README-CN.md 2021-08-23 03:14:58 +02:00
Vega
3084fdeb10
Merge pull request #30 from lonelyman0108/patch-1
Update README-CN.md
2021-08-23 08:54:07 +08:00
LM
0adf29c35b
Update README-CN.md
fix : 解决在未安装vs时会报错"Microsoft Visual C++ 14.0 is required"的问题
2021-08-23 00:54:26 +08:00
babysor00
3c86cd5bca 【bugfix】 fix bug causing non-sense output for long texts 修复多段文字发音错误 2021-08-22 23:44:25 +08:00
babysor00
21dd124360 Share a Model from community [Update Readme] 2021-08-22 20:38:13 +08:00
Vega
e501ac5f76
Update to install webrtcvad 2021-08-21 23:00:20 +08:00
Vega
81cf5ff485
Merge pull request #17 from babysor/add-code-of-conduct-1
Create CODE_OF_CONDUCT.md
2021-08-18 20:31:54 +08:00
Vega
ddc0fd8bf7
Create CODE_OF_CONDUCT.md 2021-08-18 16:37:25 +08:00
babysor00
feb1c7cb88 rename slr68 to magicdata to keep consistent naming convention
(cherry picked from commit bbdad858ebc4d0ee3b720ba22ae3e0ce9732a734)
2021-08-17 21:07:13 +08:00
Weijia Chen
e66d29872f
Merge pull request #13 from babysor/chineseinputsupport
Toolbox add Chinese character input support
2021-08-16 22:23:59 +08:00
Vega Chen
f6306b5c1e Add chinese support in readme 2021-08-16 22:22:55 +08:00
Vega Chen
57b06a29ec Built-in pretrained encoder/vocoder model 简化配置流程,预集成模型 2021-08-16 22:18:46 +08:00
Weijia Chen
b73dc6885c
Update README-CN.md 2021-08-16 11:24:06 +08:00
Weijia Chen
4f0a21969f
Upload pretrained model 2021-08-16 09:35:09 +08:00
Weijia Chen
a88e311e40
Update README-CN.md 2021-08-16 09:29:50 +08:00
unknown
aa1c345629 Add Chinese character input support 2021-08-15 22:53:40 +08:00
Nemo
96e9d74966
Merge pull request #7 from babysor/newdataset
Supporting new dataset SLR68 ! try python synthesizer_preprocess_audi…
2021-08-13 14:06:33 +08:00
babysor00
4d6da5d49b Supporting new dataset SLR68 ! try python synthesizer_preprocess_audio.py ...\slr --dataset SLR68 2021-08-13 00:46:21 +08:00
babysor00
752f5dbefb hide untest to avoid confusion when using this repro 2021-08-11 23:37:06 +08:00
babysor00
856793c9bd Refactor preprocessor of synthesizer to prepare to supprot more datasets 2021-08-11 23:33:43 +08:00
Weijia Chen
c21d2c11dd
Update note to avoid using wrong models 2021-08-11 09:51:02 +08:00
Vega Chen
67d301fc5b add instruction to use pretrained models 2021-08-09 19:46:18 +08:00
Weijia Chen
f651ebf0bf
Add demo video link (version 1) 2021-08-07 16:36:07 +08:00
Weijia Chen
0105be8661
Update training sample plots to readme 2021-08-07 12:02:34 +08:00
babysor00
e46cd609a2 Init to support Chinese Dataset. 2021-08-07 11:56:00 +08:00