github-forks
/
MockingBird
mirror of https://github.com/babysor/MockingBird.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
115 Commits
17 Branches
1 Tag
132 MiB
Commit Graph

115 Commits (9e072c26190448e4d5baad71ab098ca1bb4a1c75)
 

Author SHA1 Message Date
hertz 9e072c2619
Hifigan Support train from existed checkpoint. () 
* 1k steps to save tmp hifigan model

* hifigan support train from existed ckpt
Alex Newton b79e9d68e4
连续换行造成的多了个None () 
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
babysor00 0536874dec Add config file for pretrained
李子 4529479091
指定librosa版本 () 
* 支持data_aishell（SLR33）数据集

* 更新readme

* 指定librosa版本
babysor00 8ad9ba2b60 change naming logic of saving trained file for synthesizer to allow shorter interval
D-Blue b56ec5ee1b
Fix a UserWarning () 
Fix a UserWarning in synthesizer/synthesizer_dataset.py, because of converting list of numpy array to torch tensor at Ln.85.
CrystalRays 0bc34a5bc9
Fix TypeError at line 459 in toolbox/ui.py when both PySide6(PyQt6) and PyQt5 installed () 
### 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
Wings Music 875fe15069
Update readme for training encoder ()
zzxiang 4728863f9d
Fix inference on cpu device ()
hertz a4daf42868
1k steps to save tmp hifigan model ()
harian b50c7984ab
tacotron.py-Multi GPU with DataParallel ()
babysor00 26fe4a047d Differentiate GST token
babysor00 aff1b5313b Order of declared pytorch module matters
babysor 7dca74e032 Change default to use speaker embed for reference
babysor00 a37b26a89c 模型兼容问题加强 Compatibility Enhance of Pretrained Models and code base
babysor00 902e1eb537 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese
babysor00 5c0e53a29a Fix
DragonDreamer 4edebdfeba
修复synthesizer/models/tacotron.Encoder注释错误 () 
fix Issue#202
babysor00 6c8f3f4515 Allow to select vocoder in web
babysor00 2bd323b7df Update readme
babysor00 3674d8b5c6 Use speaker embedding anyway even with default style
babysor00 80aaf32164 Add max steps control in toolbox
babysor00 c396792b22 Upload new models
babysor00 7c58fe01d1 Concat GST output instead of adding directly with original output
Vega 724194a4de
Add code to control finetune layers ()
babysor00 31bc6656c3 Fix bug of importing GST and add more parameters in toolbox
洛竹 aa35fb3139
docs: this repo -> 本代码库 () 
Co-authored-by: 洛竹 <youngjuning@aliyun.com>
babysor00 727eafc51b Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese
babysor00 d328ecba81 Reconstruct UI of toolbox
Vega fad574118c
Update README-CN.md
babysor00 b0c156a537 Add new dataset support to preprocess parameter
Vega 724809abf4
Update README.md
Vega 05cd1a54ea
Add new pretrain model with gst
李子 245099c740
支持data_aishell（SLR33）数据集 () 
* 支持data_aishell（SLR33）数据集

* 更新readme
babysor00 6dd2af49fe Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese
babysor00 8b43ec9a64 Fix bug pre-processing magicdata
Vega 2a99f0ff05
Add gst () 
* Commit with working GST

* Make it backward compatible

* Add readme
babysor00 a824b54122 补充预处理文档
weida wang 81befb91b0
Update ui.py () 
Add minimize and maximize button of window
babysor00 e2017d0314 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main
babysor00 547ac816df Update demo and training param 
A
Ji Zhang 6b4ab39601
add alternative download source for dataset (google drive) ()
babysor00 b46e7a7866 New web with selecting wav files
babysor00 8a384a1191 Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main
Nemo 11154783d8
web tool box update UI () 
* web tool box update UI

* update img
AkifSaeed20 d52db0444e
Update launch.json ()
babysor00 790d11a58b Allow to train encoder
babysor00 cb82fcfe58 Add Zhihu link (chinese Quora) to readme
babysor00 26ecb7546d Merge branch 'main' of https://github.com/babysor/Realtime-Voice-Clone-Chinese into main
babysor00 f64914fca8 add new model