diff --git a/README.md b/README.md
index 885783d..55a2acc 100644
--- a/README.md
+++ b/README.md
@@ -83,7 +83,17 @@ model_assets
 - [ ] もしそうなら、大量の人数の音声を学習させれば、ある意味「話者空間から適当に選んだ話者（連続的に変えられる）の音声合成」ができるのでは？リファレンス音声も使えばゼロショットでの音声合成もできるのでは？
 
 
-以下本家のREADME.md
+## References
+In addition to the original reference (written below), I used the following repositories:
+- [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2)
+- [EasyBertVits2](https://github.com/Zuntan03/EasyBertVits2)
+
+The pretrained model is essentially taken from (so all the credits go to the original author(maybe Fish Audio group)):
+- https://huggingface.co/Garydesu/bert-vits2_base_model-2.1
+
+
+Below is the original README.md.
+---
 
 <div align="center">
 
diff --git a/scripts/Install-Style-Bert-VITS2.bat b/scripts/Install-Style-Bert-VITS2.bat
index 06394c2..7c85ae9 100644
--- a/scripts/Install-Style-Bert-VITS2.bat
+++ b/scripts/Install-Style-Bert-VITS2.bat
@@ -1,3 +1,6 @@
+@REM https://github.com/Zuntan03/EasyBertVits2 より引用・改変
+@REM 改行コードがLFでうまくいかないのでCRLFに変更
+
 @echo off
 chcp 65001 > NUL
 pushd %~dp0
diff --git a/scripts/Setup-Python.bat b/scripts/Setup-Python.bat
index 70d7a24..c06ccb1 100644
--- a/scripts/Setup-Python.bat
+++ b/scripts/Setup-Python.bat
@@ -1,4 +1,5 @@
 @REM https://github.com/Zuntan03/EasyBertVits2 より引用・改変
+@REM 改行コードがLFでうまくいかないのでCRLFに変更
 
 @echo off
 chcp 65001 > NUL
diff --git a/scripts/Setup.bat b/scripts/Setup.bat
index 71506d3..2d7f9e9 100644
--- a/scripts/Setup.bat
+++ b/scripts/Setup.bat
@@ -1,4 +1,5 @@
 @REM https://github.com/Zuntan03/EasyBertVits2 より引用・改変
+@REM 改行コードがLFでうまくいかないのでCRLFに変更
 
 @echo off
 chcp 65001 > NUL