refine practical en docs (#2238)

docs/practical_tutorials/image_classification_garbage_tutorial_en.md

@@ -31,7 +31,7 @@ After trying the pipeline, determine if it meets your expectations (including ac
 
 ## 3. Choosing a Model
 
-PaddleX provides 80 end-to-end image classification models, which can be referenced in the [Model List](../support_list/models_list.md). Some of the benchmarks for these models are as follows:
+PaddleX provides 80 end-to-end image classification models, which can be referenced in the [Model List](../support_list/models_list_en.md). Some of the benchmarks for these models are as follows:
 
 | Model List          | Top-1 Accuracy (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size (M) |
 | ------------------- | ------------------ | ----------------------- | ----------------------- | -------------- |

docs/practical_tutorials/ocr_det_license_tutorial.md

@@ -250,7 +250,7 @@ for res in output:
     res.save_to_img("./output/") # 保存结果可视化图像
     res.save_to_json("./output/") # 保存预测的结构化输出
 ```
-更多参数请参考 [OCR 产线使用教程](../pipeline_usage/tutorials/ocr_pipelies/OCR.md)。
+更多参数请参考 [OCR 产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/OCR.md)。
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：
 

docs/practical_tutorials/ocr_rec_chinese_tutorial.md

@@ -252,7 +252,7 @@ for res in output:
     res.save_to_img("./output/") # 保存结果可视化图像
     res.save_to_json("./output/") # 保存预测的结构化输出
 ```
-更多参数请参考 [OCR 产线使用教程](../pipeline_usage/tutorials/ocr_pipelies/OCR.md)。
+更多参数请参考 [OCR 产线使用教程](../pipeline_usage/tutorials/ocr_pipelines/OCR.md)。
 
 2. 此外，PaddleX 也提供了其他三种部署方式，详细说明如下：