diff --git a/README.md b/README.md
index 4da2fea..e186c2c 100644
--- a/README.md
+++ b/README.md
@@ -182,6 +182,7 @@ dataset_raw
     ├───...
     └───xxx7-xxx007.wav
 ```
+There are no specific restrictions on the format of the name for each audio file (naming conventions such as `000001.wav` to `999999.wav` are also valid), but the file type must be `WAV``.
 
 You can customize the speaker's name as showed below:
 
diff --git a/README_zh_CN.md b/README_zh_CN.md
index 036791f..af85e92 100644
--- a/README_zh_CN.md
+++ b/README_zh_CN.md
@@ -170,7 +170,7 @@ unzip -od pretrain/nsf_hifigan pretrain/nsf_hifigan_20221211.zip
 
 ## 📊 数据集准备
 
-仅需要以以下文件结构将数据集放入 dataset_raw 目录即可
+仅需要以以下文件结构将数据集放入 dataset_raw 目录即可。
 
 ```
 dataset_raw
@@ -183,6 +183,7 @@ dataset_raw
     ├───...
     └───xxx7-xxx007.wav
 ```
+对于每一个音频文件的名称并没有格式的限制(`000001.wav`~`999999.wav`之类的命名方式也是合法的)，不过文件类型必须是`wav`。
 
 可以自定义说话人名称