Updata Readme

This commit is contained in:
ylzz1997 2023-07-23 23:10:22 +08:00
parent 317cde248d
commit 6a8dfc7ea3
2 changed files with 5 additions and 1 deletions

View File

@ -177,7 +177,9 @@ If you are using the `rmvpe` F0 Predictor, you will need to download the pre-tra
##### FCPE
If you are using the `fcpe` F0 Predictor, you will need to download the pre-trained RMVPE model.
[FCPE(Fast Context-base Pitch Estimator)](https://github.com/CNChTu/MelPE) is a dedicated F0 predictor designed for real-time voice conversion and will become the preferred F0 predictor for sovits real-time voice conversion in the future.
If you are using the `fcpe` F0 Predictor, you will need to download the pre-trained FCPE model.
- download model at [fcpe.pt](https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/fcpe.pt)
- Place it under the `pretrain` directory

View File

@ -180,6 +180,8 @@ unzip -od pretrain/nsf_hifigan pretrain/nsf_hifigan_20221211.zip
> 你说的对,但是[FCPE](https://github.com/CNChTu/MelPE)是由svc-develop-team自主研发的一款全新的F0预测器后面忘了
[FCPE(Fast Context-base Pitch Estimator)](https://github.com/CNChTu/MelPE)是一个为实时语音转换所设计的专用F0预测器他将在未来成为Sovits实时语音转换的首选F0预测器.
如果使用 `fcpe` F0预测器的话需要下载预训练的 FCPE 模型
+ 下载模型 [fcpe.pt](https://huggingface.co/datasets/ylzz1997/rmvpe_pretrain_model/resolve/main/fcpe.pt)