Commit Graph

Select branches

Hide Pull Requests

Add-GST

babysor-patch-1

babysor-patch-2

babysor-patch-3

babysor-patch-4

babysor-patch-5

babysor-patch-6

babysor-patch-7

babysor-patch-8

biaobei

chineseinputsupport

dev

dev-fix

fregan

main

ppg-vc-init

refactor

restruct-project

webtoolbox

#1004

#1004

#1005

#1007

#1009

#1011

#102

#1022

#1023

#1023

#1028

#1030

#109

#110

#111

#112

#13

#136

#137

#141

#154

#157

#17

#194

#198

#198

#203

#231

#240

#241

#250

#255

#273

#29

#296

#296

#30

#315

#316

#32

#375

#378

#379

#38

#389

#405

#421

#470

#498

#505

#520

#523

#529

#544

#546

#548

#549

#558

#560

#568

#568

#579

#609

#610

#610

#628

#633

#633

#640

#649

#650

#660

#663

#698

#7

#705

#715

#72

#741

#743

#747

#748

#75

#75

#751

#76

#782

#790

#795

#802

#822

#83

#84

#860

#892

#908

#913

#914

#93

#94

#944

#945

#947

#95

#950

#951

#952

#953

#96

#98

#988

#989

#99

v0.0.1

Mono Color

• 78fcfc4651 remove unused sample audios and mark deprecated files babysor00 2021-09-11 22:59:09 +08:00
• 45bc43bf3c Add description of new vocoder and pretrained models babysor00 2021-09-08 23:36:35 +08:00
• dacedfa9cc Merge pull request #76 from PeijiYang/main Vega 2021-09-08 23:06:14 +08:00
• b60b75ea89 remove hardcode and unused part peijiyang 2021-09-08 11:17:20 +08:00
• c4a8c72b83 add pretrained hifigan peijiyang 2021-09-07 21:50:31 +08:00
• 8195a55a25 add hifigan vocoder peijiyang 2021-09-07 21:41:16 +08:00
• 53fe291d3c Add proprocess_transcript file biaobei babysor00 2021-09-02 09:40:12 +08:00
• bd0e47e76b Support new dataset "biaobei" BZNSYP High quality single speaker for Chinese babysor00 2021-09-01 23:44:40 +08:00
• 024d88ae96 Ignore vocoder models except pretrained Nemo 2021-09-01 08:44:43 +08:00
• 5c0cb50c3e Add quick path to preprocess audio, denoise audio when loading in toolbox babysor00 2021-08-30 22:22:06 +08:00
• 2f1f4f70b4 add support of aishell, magic data in toolbox babysor00 2021-08-29 16:31:40 +08:00
• 4132bd113f Add readme instruction to train vocoder babysor00 2021-08-29 15:48:11 +08:00
• 5950eea895 Support training your own vocoder babysor00 2021-08-29 15:43:54 +08:00
• 630023c7b2 format readme and add paper references babysor00 2021-08-29 10:55:59 +08:00
• 17d47589c1 Fix compatibility issue of symbols babysor00 2021-08-29 00:45:49 +08:00
• 0bba0a806e Update README.md Nemo 2021-08-28 19:56:19 +08:00
• 331e1d4238 Update README-CN.md Nemo 2021-08-28 19:55:42 +08:00
• 2130908449 Add newbie friendly version Vega 2021-08-28 09:40:44 +08:00
• 95bbcf6cd8 Add readme to support aishell3 Nemo 2021-08-25 23:14:30 +08:00
• a6f8c8a39a Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main Nemo 2021-08-25 23:11:34 +08:00
• 0cc3f569fa [dataset]support aishell3(tested) Nemo 2021-08-25 23:11:29 +08:00
• c3fb378b63 Update README-CN.md Vega 2021-08-24 00:03:13 +08:00
• 9f30ca8e92 Merge pull request #38 from XiuChen-Liu/main Vega 2021-08-23 16:48:41 +08:00
• 0ede0ad771 UPDATE README.md XiuChen-Liu 2021-08-23 15:37:33 +08:00
• 16c1d2049f UPDATE README-CN.md XiuChen-Liu 2021-08-23 15:37:16 +08:00
• a810e6a472 Merge pull request #32 from Nthily/main Vega 2021-08-23 13:14:38 +08:00
• 4f23833a69 Update README.md Nthily 2021-08-23 03:17:32 +02:00
• e25072a4a8 Update README-CN.md Nthily 2021-08-23 03:16:35 +02:00
• 289ededebc Update README-CN.md Nthily 2021-08-23 03:14:58 +02:00
• 3084fdeb10 Merge pull request #30 from lonelyman0108/patch-1 Vega 2021-08-23 08:54:07 +08:00
• 0adf29c35b Update README-CN.md LM 2021-08-23 00:54:26 +08:00
• 3c86cd5bca 【bugfix】 fix bug causing non-sense output for long texts 修复多段文字发音错误 babysor00 2021-08-22 23:44:25 +08:00
• 21dd124360 Share a Model from community [Update Readme] babysor00 2021-08-22 20:37:34 +08:00
• e501ac5f76 Update to install webrtcvad Vega 2021-08-21 23:00:20 +08:00
• 81cf5ff485 Merge pull request #17 from babysor/add-code-of-conduct-1 Vega 2021-08-18 20:31:54 +08:00
• ddc0fd8bf7 Create CODE_OF_CONDUCT.md Vega 2021-08-18 16:37:25 +08:00
• feb1c7cb88 rename slr68 to magicdata to keep consistent naming convention babysor00 2021-08-17 20:55:28 +08:00
• e66d29872f Merge pull request #13 from babysor/chineseinputsupport Weijia Chen 2021-08-16 22:23:59 +08:00
• f6306b5c1e Add chinese support in readme chineseinputsupport Vega Chen 2021-08-16 22:22:55 +08:00
• 57b06a29ec Built-in pretrained encoder/vocoder model 简化配置流程,预集成模型 Vega Chen 2021-08-16 22:18:46 +08:00
• b73dc6885c Update README-CN.md Weijia Chen 2021-08-16 11:24:06 +08:00
• 4f0a21969f Upload pretrained model Weijia Chen 2021-08-16 09:35:09 +08:00
• a88e311e40 Update README-CN.md Weijia Chen 2021-08-16 09:29:50 +08:00
• aa1c345629 Add Chinese character input support unknown 2021-08-15 22:53:40 +08:00
• 96e9d74966 Merge pull request #7 from babysor/newdataset Nemo 2021-08-13 14:06:33 +08:00
• 4d6da5d49b Supporting new dataset SLR68 ! try python synthesizer_preprocess_audio.py ...\slr --dataset SLR68 babysor00 2021-08-13 00:41:58 +08:00
• 752f5dbefb hide untest to avoid confusion when using this repro babysor00 2021-08-11 23:37:06 +08:00
• 856793c9bd Refactor preprocessor of synthesizer to prepare to supprot more datasets babysor00 2021-08-11 23:33:43 +08:00
• c21d2c11dd Update note to avoid using wrong models Weijia Chen 2021-08-11 09:51:02 +08:00
• 67d301fc5b add instruction to use pretrained models Vega Chen 2021-08-09 19:46:18 +08:00
• f651ebf0bf Add demo video link (version 1) Weijia Chen 2021-08-07 16:36:07 +08:00
• 0105be8661 Update training sample plots to readme Weijia Chen 2021-08-07 12:02:34 +08:00
• e46cd609a2 Init to support Chinese Dataset. babysor00 2021-08-07 11:56:00 +08:00