Bert-VITS2-Audio-Generator
GUI TTS application based on:
Bert-VITS2 (https://github.com/fishaudio/Bert-VITS2)
PyQt-Fluent-Widgets (https://github.com/zhiyiYo/PyQt-Fluent-Widgets)
Update
-
Version 1.1 is released
Download app_v11.exe
Replace the original app.exe by app_v11.exe
以app_v11.exe取代原有的app.exe
If multi-speaker model is used, please configure n_speaker and spk2id in configs/config.json
如果使用多人模型,請先到configs/config.json修改n_speaker和spk2id
Install
-
Bert-VITS2-Audio-Generator.zip
Download Here (Google Drive)
Download Here (百度網盤/提取碼︰dx37)
Suitable for who knows nothing about the deployment of Bert-VITS2
Download, Extract, Run app.exe
適合對Bert-VITS2部署一無所知的朋友
下載,解壓,運行app.exe
-
Bert-VITS2-Audio-Generator_withoutLargeModelFiles.zip
Large model files:
bert/chinese-roberta-wwm-ext-large/pytorch_model.bin: Download Link
bert/deberta-v2-large-japanese/pytorch_model.bin: Download Link
bert/deberta-v3-large/pytorch_model.bin: Download Link
Suitable for who has already deployed Bert-VITS2 locally
Move the pytorch_model.bin files to correct places, then Run app.exe
(Note that NOT to rename the .bin files and DO NOT mix them up)
適合已經本地部署Bert-VITS2的朋友
將以上幾個pytorch_model.bin文件放到正確的位置,然後運行app.exe
(注意請不要更改文件名字,也不要把它們弄混)
The location of bert:
-
Source Code
Suitable for who is familiar with Python
You have to download the large model files listed above
requirements.txt is provided
Run app.py
適合熟悉Python的朋友
需要自行下載上面所列的幾個模型文件
已提供requirements.txt
運行app.py