diff --git a/doc/doc_ch/algorithm_rec_rfl.md b/doc/doc_ch/algorithm_rec_rfl.md
index 5135e77a1..0906d4570 100644
--- a/doc/doc_ch/algorithm_rec_rfl.md
+++ b/doc/doc_ch/algorithm_rec_rfl.md
@@ -41,7 +41,7 @@
 <a name="3-1"></a>
 ### 3.1 模型训练
 
-请参考[文本识别训练教程](./recognition.md)。PaddleOCR对代码进行了模块化，训练`RFL`识别模型时需要**更换配置文件**为`RFL`的[配置文件](../../configs/rec/rec_resnet_rfl_att.yml)。
+PaddleOCR对代码进行了模块化，训练`RFL`识别模型时需要**更换配置文件**为`RFL`的[配置文件](../../configs/rec/rec_resnet_rfl_att.yml)。
 
 #### 启动训练
 
diff --git a/doc/doc_en/algorithm_rec_rfl_en.md b/doc/doc_en/algorithm_rec_rfl_en.md
index 8f0adfbe3..273210c6c 100644
--- a/doc/doc_en/algorithm_rec_rfl_en.md
+++ b/doc/doc_en/algorithm_rec_rfl_en.md
@@ -36,7 +36,7 @@ Please refer to ["Environment Preparation"](./environment_en.md) to configure th
 <a name="3"></a>
 ## 3. Model Training / Evaluation / Prediction
 
-Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**.
+PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**.
 
 Training: