diff --git a/README.md b/README.md
index 8388a91..258d09d 100644
--- a/README.md
+++ b/README.md
@@ -199,11 +199,12 @@ dataset
 You can customize the speaker name.
 
 ```
-dataset_raw
-└───suijiSUI
-    ├───1.wav
-    ├───...
-    └───25788785-20221210-200143-856_01_(Vocals)_0_0.wav
+dataset
+└───44k
+     └───suijiSUI
+           ├───1.wav
+           ├───...
+           └───25788785-20221210-200143-856_01_(Vocals)_0_0.wav
 ```
 
 ### 2. Automatically split the dataset into training and validation sets, and generate configuration files.
diff --git a/README_zh_CN.md b/README_zh_CN.md
index ac5e1b7..be0c6d6 100644
--- a/README_zh_CN.md
+++ b/README_zh_CN.md
@@ -201,11 +201,12 @@ dataset
 可以自定义说话人名称
 
 ```
-dataset_raw
-└───suijiSUI
-    ├───1.wav
-    ├───...
-    └───25788785-20221210-200143-856_01_(Vocals)_0_0.wav
+dataset
+└───44k
+     └───suijiSUI
+           ├───1.wav
+           ├───...
+           └───25788785-20221210-200143-856_01_(Vocals)_0_0.wav
 ```
 
 ### 2. 自动划分训练集、验证集，以及自动生成配置文件