Commit Graph

202 Commits (cc250af1f66e6afac4948e5d298ca2e1b3d47d0a)
 

Author SHA1 Message Date
wenqingl 400a7207e3
Update README.md (#640) 3 years ago
babysor00 6f023e313d Add web gui of training and reconstruct taco model methods 3 years ago
babysor00 a39b6d3117 Remove breaking import for Macos 3 years ago
babysor00 885225045d 修复兼容性 - mac + linux 3 years ago
babysor00 ee643d7cbc Fix compatibility issue 3 years ago
flysmart 6a793cea84
Added missing files for Fre-GAN (#579)
* 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
3 years ago
Evers 7317ba5ffe
add gen_voice.py for handle by python command instead of demon_tool gui. (#560) 3 years ago
flysmart 05f886162c
GAN training now supports DistributedDataParallel (DDP) (#558)
* 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
3 years ago
babysor00 e726c2eb12 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese 3 years ago
babysor00 c00474525a Fix nits of file path 3 years ago
flysmart 350b190662
Solved the problem that the existing model could not be loaded when training the GAN model (#549)
* 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
3 years ago
flysmart 0caed984e3
The new vocoder Fre-GAN is now supported (#546)
* The new vocoder Fre-GAN is now supported

* Improved some fregan details
3 years ago
Vega c5d03fb3cb
Upgrade to new web service (#529)
* 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
3 years ago
babysor00 7f799d322f Tell the hifigan type of a vocoder model by searching full text 3 years ago
LZY a1f2e4a790
Update README-CN.md (#523) 3 years ago
Lix Zhou b136f80f43
Add an aliyunpan download link (#505)
Baidu Yun Pan is so fxxking slow
3 years ago
Moose W. Oler f082a82420
fix issue #496 (#498)
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.
3 years ago
babysor00 7f0d983da7 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese 3 years ago
babysor00 0353bfc6e6 New GUI in order to combine web and toolbox in future 3 years ago
Vega 9ec114a7c1
Create FUNDING.yml 3 years ago
1itt1eB0y ddf612e87c
Update README-CN.md (#470)
修正一个简单的翻译问题
3 years ago
babysor00 374cc89cfa Fix web generate with rnn bug 3 years ago
babysor00 6009da7072 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese 3 years ago
babysor00 1c61a601d1 Remove dependency of pyworld for non-vc mode 3 years ago
Vega 02ee514aa3
Update issue templates 3 years ago
babysor00 6532d65153 Add default param for inferencing of vocoder 3 years ago
babysor00 3fe0690cc6 Update README-CN.md 3 years ago
babysor00 79f424d614 Add default path for hifi 3 years ago
babysor00 3c97d22938 Fix bug when searching for vocoder 3 years ago
babysor00 fc26c38152 Fix compatibility issue 3 years ago
babysor00 6c01b92703 Fix bug introduced by config file reading 3 years ago
babysor00 c36f02634a Add link and separate requirement file 3 years ago
Vega b05e7441ff
Fix nit in readme 3 years ago
Vega 693de98f4d
Add instruction image 3 years ago
Vega 252a5e11b3
Ppg vc init (#421)
* Init  ppg extractor and ppg2mel

* add preprocess and training

* FIx known issues

* Update __init__.py

Allow to gen audio

* Fix length issue

* Fix bug of preparing fid

* Fix sample issues

* Add UI usage of PPG-vc

* Add readme
3 years ago
Vega b617a87ee4
Init ppg extractor and ppg2mel (#375)
* Init  ppg extractor and ppg2mel

* add preprocess and training

* FIx known issues

* Update __init__.py

Allow to gen audio

* Fix length issue

* Fix bug of preparing fid

* Fix sample issues

* Add UI usage of PPG-vc
3 years ago
AyahaShirane ad22997614
fixed the issues #372 (#379)
修复了一些参数传递造成的问题,把过时的torch.nn.functional.tanh()改成了torch.tanh()
3 years ago
hertz 9e072c2619
Hifigan Support train from existed checkpoint. (#389)
* 1k steps to save tmp hifigan model

* hifigan support train from existed ckpt
3 years ago
Alex Newton b79e9d68e4
连续换行造成的多了个None (#405)
小问题,gui好像没有这个问题,自己测试web的时候直接调用的函数发现的这个情况
3 years ago
babysor00 0536874dec Add config file for pretrained 3 years ago
李子 4529479091
指定librosa版本 (#378)
* 支持data_aishell(SLR33)数据集

* 更新readme

* 指定librosa版本
3 years ago
babysor00 8ad9ba2b60 change naming logic of saving trained file for synthesizer to allow shorter interval 3 years ago
D-Blue b56ec5ee1b
Fix a UserWarning (#273)
Fix a UserWarning in synthesizer/synthesizer_dataset.py, because of converting list of numpy array to torch tensor at Ln.85.
3 years ago
CrystalRays 0bc34a5bc9
Fix TypeError at line 459 in toolbox/ui.py when both PySide6(PyQt6) and PyQt5 installed (#255)
### Error Info Screenshot
![](https://cdn.jsdelivr.net/gh/CrystalRays/CDN@main/img/16389623959301638962395845.png)

### Error Reason
Matplotlib.backends.qt_compat.py decide the version of qt library according to sys.modules firstly, os.environ secondly and the sequence of PyQt6, PySide6, PyQt5, PySide 2 and etc finally. Import PyQt5 after matplotlib make that there is no PyQt5 in sys.modules so that it choose PyQt6 or PySide6 before PyQt5 if it installed.
因为Matplotlib.backends.qt_compat.py优先根据导入的库决定要使用的Python Qt的库,如果没有导入则根据环境变量PYQT_APT决定,再不济就按照PyQt6, PySide6, PyQt5, PySide 2的顺序导入已经安装的库。因为ui.py先导入matplotlib而不是PYQT5导致matplotlib在导入的库里找不到Qt的库,又没有指定环境变量,然后用户安装了Qt6的库的话就导入Qt6的库去了
3 years ago
Wings Music 875fe15069
Update readme for training encoder (#250) 3 years ago
zzxiang 4728863f9d
Fix inference on cpu device (#241) 3 years ago
hertz a4daf42868
1k steps to save tmp hifigan model (#240) 3 years ago
harian b50c7984ab
tacotron.py-Multi GPU with DataParallel (#231) 3 years ago
babysor00 26fe4a047d Differentiate GST token 3 years ago
babysor00 aff1b5313b Order of declared pytorch module matters 3 years ago