diff --git a/fastdeploy/vision/ocr/ppocr/classifier.cc b/fastdeploy/vision/ocr/ppocr/classifier.cc
index d0d9d9016..435f18444 100644
--- a/fastdeploy/vision/ocr/ppocr/classifier.cc
+++ b/fastdeploy/vision/ocr/ppocr/classifier.cc
@@ -31,7 +31,7 @@ Classifier::Classifier(const std::string& model_file,
     valid_gpu_backends = {Backend::ORT, Backend::TRT};  // 指定可用的GPU后端
   } else {
     valid_cpu_backends = {Backend::PDINFER, Backend::ORT, Backend::OPENVINO};
-    valid_gpu_backends = {Backend::PDINFER, Backend::TRT, Backend::ORT};
+    valid_gpu_backends = {Backend::PDINFER, Backend::ORT, Backend::TRT};
   }
   runtime_option = custom_option;
   runtime_option.model_format = model_format;
diff --git a/fastdeploy/vision/ocr/ppocr/recognizer.cc b/fastdeploy/vision/ocr/ppocr/recognizer.cc
index 84b90afee..8202ece6b 100644
--- a/fastdeploy/vision/ocr/ppocr/recognizer.cc
+++ b/fastdeploy/vision/ocr/ppocr/recognizer.cc
@@ -48,9 +48,8 @@ Recognizer::Recognizer(const std::string& model_file,
                           Backend::OPENVINO};  // 指定可用的CPU后端
     valid_gpu_backends = {Backend::ORT, Backend::TRT};  // 指定可用的GPU后端
   } else {
-    // NOTE:此模型暂不支持paddle-inference-Gpu推理
-    valid_cpu_backends = {Backend::ORT, Backend::PDINFER, Backend::OPENVINO};
-    valid_gpu_backends = {Backend::ORT, Backend::TRT};
+    valid_cpu_backends = {Backend::PDINFER, Backend::ORT, Backend::OPENVINO};
+    valid_gpu_backends = {Backend::PDINFER, Backend::ORT, Backend::TRT};
   }
 
   runtime_option = custom_option;