Merge pull request #375 from CNChTu/4.1-Fork

updata readme

README.md

@@ -182,7 +182,13 @@ If you are using the `rmvpe` F0 Predictor, you will need to download the pre-tra
 
 ##### FCPE(Preview version)
 
-[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.(The paper is being written)
+[FCPE(Fast Context-base Pitch Estimator)](https://github.com/CNChTu/MelPE) is a dedicated F0 predictor designed for real-time voice conversion and has been the preferred F0 predictor for sovits real-time voice conversion.(The paper is being written)
+
+The GUI for real-time voice conversion is `gui.py`.
+
+```shell
+python gui.py
+```
 
 If you are using the `fcpe` F0 Predictor, you will need to download the pre-trained FCPE model.
 

README_zh_CN.md

@@ -185,7 +185,13 @@ 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.（论文未来会有的）
+[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，他是Sovits实时语音转换的首选F0预测器.（论文未来会有的）
+
+实时语音转换的gui是`gui.py`
+
+```shell
+python gui.py
+```
 
 如果使用 `fcpe` F0预测器的话，需要下载预训练的 FCPE 模型
 

gui.py

@@ -2,9 +2,6 @@ import json
 import os
 import pickle
 import threading
-
-# from ddsp.vocoder import load_model, F0_Extractor, Volume_Extractor, Units_Encoder
-# from ddsp.core import upsample
 import time
 
 import librosa

requirements.txt

@@ -28,4 +28,6 @@ pyyaml
 pynvml
 faiss-cpu
 einops
-local_attention
+local_attention
+PySimpleGUI
+sounddevice

requirements_win.txt

@@ -31,3 +31,5 @@ langdetect
 pyyaml
 pynvml
 faiss-cpu
+PySimpleGUI
+sounddevice