diff --git a/python/examples/ocr/README.md b/python/examples/ocr/README.md
index dd9deea264db776a656f0736745e93311bd23684..605b4abe7c12cf2a9b0d8d0d02a2fe9c04b76723 100755
--- a/python/examples/ocr/README.md
+++ b/python/examples/ocr/README.md
@@ -111,7 +111,7 @@ After the -- model parameter, the folder path of multiple model files is passed
 #for cpu user
 python -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model --port 9293
 #for gpu user
-python -m paddle_serving_server_gpu.serve --model ocr_det_model ocr_rec_model --port 9293 --gpu_id 0
+python -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model --port 9293 --gpu_id 0
 ```
 
 ### Client Prediction
diff --git a/python/examples/ocr/README_CN.md b/python/examples/ocr/README_CN.md
index 0a7abc9c01617421a9f8811401c90584ea4ed1ed..ad7ddcee21dd2f514d2ab8f63a732ee93349abac 100755
--- a/python/examples/ocr/README_CN.md
+++ b/python/examples/ocr/README_CN.md
@@ -110,7 +110,7 @@ python rec_web_client.py
 #for cpu user
 python -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model --port 9293
 #for gpu user
-python -m paddle_serving_server_gpu.serve --model ocr_det_model ocr_rec_model --port 9293 --gpu_id 0
+python -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model --port 9293 --gpu_id 0
 ```
 
 ### 启动客户端