Commit Graph

177 Commits (9f1dbeeecc902b2719f77e93996bb74b6d654426)
 

Author SHA1 Message Date
0warning0error 9f1dbeeecc Some changes to make it easier to install the dependencies
Vega b78d0d2a26
Merge pull request from Nier-Y/main
Update README.md and README-CN.md
babysor00 5c17fc8bb0 add pretrained
babysor00 3ce874ab46 Fix issue for training and preprocessing
babysor00 beec0b93ed Fix issues
Vega 9d67b757f0
Merge pull request from babysor/restruct-project
Restruct project
Vega 26331fe019
Merge branch 'main' into restruct-project
babysor00 712a53f557 Add vits
babysor00 24cb262c3f remove used files
babysor00 e469bd06ae init
神楽坂·喵 cd20d21f3d
add docker support ()
* add docker support

* 修复训练集解压问题

* 修复web.py启动问题

* 混合数据集训练参数
babysor00 74a3fc97d0 Refactor Project to 3 parts: Models, Control, Data
Need readme
李子 b402f9dbdf
修复web界面vc模式不能用问题。改拼写错误、给字符串前加f标 ()
yan d1ba355c5f Adding English version M1 Mac Setup
yan 83d95c6c81 新增M1 Mac的环境配置
wei-z 85a53c9e05
update aidatatang_200zh folders ()
Co-authored-by: wei-z-git <wei-z>
xxxxx 028b131570
Update streamlit_ui.py ()
Dong 2a1890f9e1
Update README-CN.md ()
修正文档复选框格式
wei-z c91bc3208e
添加 -d 指定数据集时错误提示 ()
* 添加 -d 指定数据集时错误提示

Warning: you do not have any of the recognized datasets in G:\AI\Dataset\aidatatang_200zh\aidatatang_200zh 
Please note use 'E:\datasets' as root path instead of 'E:\datasetsidatatang_200zh\corpus/test' as a example .
The recognized datasets are:

* Update ui.py

* Update ui.py
XCwosjw dd1ea3e714
更正错误的CPU型号 ()
11770k😂😂😂
Vega e7313c514f
Refactor ()
* Refactor model

* Add description for

* update launch json

* Fix 

* Avoid recursive calls of web ui for M1
Xu Meng f57d1a69b6
Translate update README-CN.md ()
Fix: Traditional Chinese to Simplified Chinese
Vega ab7d692619
Refactor ()
* Refactor model

* Add description for

* update launch json

* Fix 
Vega f17e3b04e1
Refactor ()
* Refactor model

* Add description for

* update launch json
Vega 6abdd0ebf0
Refactor ()
* Refactor model

* Refactor and fix bug to save plots
wenqingl 400a7207e3
Update README.md ()
babysor00 6f023e313d Add web gui of training and reconstruct taco model methods
babysor00 a39b6d3117 Remove breaking import for Macos
babysor00 885225045d 修复兼容性 - mac + linux
babysor00 ee643d7cbc Fix compatibility issue
flysmart 6a793cea84
Added missing files for Fre-GAN ()
* The new vocoder Fre-GAN is now supported

* Improved some fregan details

* Fixed the problem that the existing model could not be loaded to continue training when training GAN

* Updated reference papers

* GAN training now supports DistributedDataParallel (DDP)

* Added requirements.txt

* GAN training uses single card training by default

* Added note about GAN vocoder training with multiple GPUs

* Added missing files for Fre-GAN
Evers 7317ba5ffe
add gen_voice.py for handle by python command instead of demon_tool gui. ()
flysmart 05f886162c
GAN training now supports DistributedDataParallel (DDP) ()
* The new vocoder Fre-GAN is now supported

* Improved some fregan details

* Fixed the problem that the existing model could not be loaded to continue training when training GAN

* Updated reference papers

* GAN training now supports DistributedDataParallel (DDP)

* Added requirements.txt

* GAN training uses single card training by default

* Added note about GAN vocoder training with multiple GPUs
babysor00 e726c2eb12 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese
babysor00 c00474525a Fix nits of file path
flysmart 350b190662
Solved the problem that the existing model could not be loaded when training the GAN model ()
* The new vocoder Fre-GAN is now supported

* Improved some fregan details

* Fixed the problem that the existing model could not be loaded to continue training when training GAN

* Updated reference papers
flysmart 0caed984e3
The new vocoder Fre-GAN is now supported ()
* The new vocoder Fre-GAN is now supported

* Improved some fregan details
Vega c5d03fb3cb
Upgrade to new web service ()
* Init new GUI

* Remove unused codes

* Reset layout

* Add samples

* Make framework to support multiple pages

* Add vc mode

* Add preprocessing mode

* Add training mode

* Remove text input in vc mode

* Add entry for GUI and revise readme

* Move requirement together

* Add error raise when no model folder found

* Add readme
babysor00 7f799d322f Tell the hifigan type of a vocoder model by searching full text
LZY a1f2e4a790
Update README-CN.md ()
Lix Zhou b136f80f43
Add an aliyunpan download link ()
Baidu Yun Pan is so fxxking slow
Moose W. Oler f082a82420
fix issue ()
pass `wav`, `sampling_rate` (in encoder/audio.py line 59 ) as keyword args instead of postional args to prevent warning messages from massing up console outputs while adopting librosa 0.9.1 occasionally.
babysor00 7f0d983da7 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese
babysor00 0353bfc6e6 New GUI in order to combine web and toolbox in future
Vega 9ec114a7c1
Create FUNDING.yml
1itt1eB0y ddf612e87c
Update README-CN.md ()
修正一个简单的翻译问题
babysor00 374cc89cfa Fix web generate with rnn bug
babysor00 6009da7072 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese
babysor00 1c61a601d1 Remove dependency of pyworld for non-vc mode
Vega 02ee514aa3
Update issue templates