backup/Realtime-Voice-Clone-Chinese
1
0
Fork 0
mirror of https://github.com/babysor/Realtime-Voice-Clone-Chinese.git synced 2026-06-14 22:27:05 +08:00
Code Issues Projects Releases Wiki Activity

Add link and separate requirement file

Browse Source
This commit is contained in:
babysor00
2022-03-05 12:20:09 +08:00
parent b05e7441ff
commit c36f02634a
3 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README-CN.md
View File

@@ -101,7 +101,7 @@
### 4. 番外：语音转换Voice Conversion(PPG based)
想像柯南拿着变声器然后发出毛利小五郎的声音吗？本项目现基于PPG-VC，引入额外两个模块（PPG extractor + PPG2Mel）, 可以实现变声功能。（文档不全，尤其是训练部分，正在努力补充中）
#### 4.0 准备环境
* 确保项目以上环境已经安装ok，运行`pip install -r requirements.txt` 来安装剩余的必要包。
* 确保项目以上环境已经安装ok，运行`pip install -r requirements_vc.txt` 来安装剩余的必要包。
* 下载以下模型
* 24K采样率专用的vocoder（hifigan）到 *vocoder\saved_mode\xxx*
* 预训练的ppg特征encoder(ppg_extractor)到 *ppg_extractor\saved_mode\xxx*

3
requirements.txt
View File

@@ -21,6 +21,3 @@ flask_cors==3.0.10
gevent==21.8.0
flask_restx
tensorboard
PyYAML==5.4.1
torch_complex
espnet

3
requirements_vc.txt Normal file
View File

@@ -0,0 +1,3 @@
PyYAML==5.4.1
torch_complex
espnet