Nofated095
/
so-vits-svc
mirror of https://github.com/svc-develop-team/so-vits-svc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Updata Readme

This commit is contained in:
ylzz1997 2023-06-04 19:13:08 +08:00
parent 25ccad3d05
commit 03fbd1aaf2
2 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@ -73,6 +73,9 @@ After conducting tests, we believe that the project runs stably on `Python 3.8.9
**The following encoder needs to select one to use**
##### **1. If using contentvec as speech encoder(recommended)**
`vec768l12` and `vec256l9` require the encoder
- ContentVec: [checkpoint_best_legacy_500.pt](https://ibm.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr)
- Place it under the `pretrain` directory
@ -91,8 +94,8 @@ wget -P pretrain/ http://obs.cstcloud.cn/share/obs/sankagenkeshi/checkpoint_best
- Place it under the `pretrain` directory
##### **3. If whisper-ppg as the encoder**
- download model at [medium.pt](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt)
- or download model at [large-v2.pt](https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt)(choose 'whisper-ppg-large')
- download model at [medium.pt](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt), the model fits `whisper-ppg`
- or download model at [large-v2.pt](https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt), the model fits `whisper-ppg-large`
- Place it under the `pretrain` director
##### **4. If cnhubertlarge as the encoder**
@ -119,6 +122,7 @@ wget -P pretrain/ http://obs.cstcloud.cn/share/obs/sankagenkeshi/checkpoint_best
- "whisper-ppg"
- "cnhubertlarge"
- "dphubert"
- "whisper-ppg-large"
#### **Optional(Strongly recommend)**
@ -209,7 +213,7 @@ python resample.py --skip_loudnorm
python preprocess_flist_config.py --speech_encoder vec768l12
```
speech_encoder has 6 choices
speech_encoder has 7 choices
```
vec768l12
@ -218,6 +222,7 @@ hubertsoft
whisper-ppg
cnhubertlarge
dphubert
whisper-ppg-large
```
If the speech_encoder argument is omitted, the default value is vec768l12

13
README_zh_CN.md
View File

@ -75,6 +75,9 @@
**以下编码器需要选择一个使用**
##### **1. 若使用contentvec作为声音编码器（推荐）**
`vec768l12`与`vec256l9` 需要该编码器
+ contentvec ：[checkpoint_best_legacy_500.pt](https://ibm.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr)
+ 放在`pretrain`目录下
@ -93,8 +96,8 @@ wget -P pretrain/ http://obs.cstcloud.cn/share/obs/sankagenkeshi/checkpoint_best
+ 放在`pretrain`目录下
##### **3. 若使用Whisper-ppg作为声音编码器**
+ 下载模型 [medium.pt](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt)
+ 或者下载模型 [large-v2.pt](https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt)（设置时选择‘whisper-ppg-large’）
+ 下载模型 [medium.pt](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt), 该模型适配`whisper-ppg`
+ 下载模型 [large-v2.pt](https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt), 该模型适配`whisper-ppg-large`
+ 放在`pretrain`目录下
##### **4. 若使用cnhubertlarge作为声音编码器**
@ -121,7 +124,8 @@ wget -P pretrain/ http://obs.cstcloud.cn/share/obs/sankagenkeshi/checkpoint_best
- "whisper-ppg"
- "cnhubertlarge"
- "dphubert"
- "whisper-ppg-large"
#### **可选项(强烈建议使用)**
+ 预训练底模文件： `G_0.pth` `D_0.pth`
@ -211,13 +215,14 @@ python resample.py --skip_loudnorm
python preprocess_flist_config.py --speech_encoder vec768l12
```
speech_encoder拥有六个选择
speech_encoder拥有七个选择
```
vec768l12
vec256l9
hubertsoft
whisper-ppg
whisper-ppg-large
cnhubertlarge
dphubert
```