fix sar export

doc/doc_ch/algorithm_rec_sar.md

@@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_r31_sar.yml -o Global.pretraine
 SAR文本识别模型推理，可以执行如下命令：
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_char_type="ch" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False
 ```
 
 <a name="4-2"></a>

doc/doc_en/algorithm_rec_sar_en.md

@@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_r31_sar.yml -o Global.pretraine
 For SAR text recognition model inference, the following commands can be executed:
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_char_type="ch" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False
 ```
 
 <a name="4-2"></a>

tools/export_model.py

@@ -58,6 +58,8 @@ def export_single_model(model,
         other_shape = [
             paddle.static.InputSpec(
                 shape=[None, 3, 48, 160], dtype="float32"),
+            [paddle.static.InputSpec(
+                shape=[None], dtype="float32")]
         ]
         model = to_static(model, input_spec=other_shape)
     elif arch_config["algorithm"] == "SVTR":

tools/infer/predict_rec.py

@@ -349,7 +349,8 @@ class TextRecognizer(object):
                 valid_ratios = np.concatenate(valid_ratios)
                 inputs = [
                     norm_img_batch,
-                    valid_ratios,
+                    np.array(
+                        [valid_ratios], dtype=np.float32),
                 ]
                 if self.use_onnx:
                     input_dict = {}