diff --git a/doc/doc_ch/algorithm_rec_visionlan.md b/doc/doc_ch/algorithm_rec_visionlan.md
index df039491d49e192349d57b44cc448c57e4211098..84b5ef68216972da982f9f1d902fddea7e107be9 100644
--- a/doc/doc_ch/algorithm_rec_visionlan.md
+++ b/doc/doc_ch/algorithm_rec_visionlan.md
@@ -139,7 +139,7 @@ Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.9999493)
 ## 5. FAQ
 
 1. MJSynth和SynthText两种数据集来自于[VisionLAN源repo](https://github.com/wangyuxin87/VisionLAN) 。
-2. 我们使用VisionLAN作者提供的预训练模型进行finetune训练。
+2. 我们使用VisionLAN作者提供的预训练模型进行finetune训练，预训练模型配套字典为'ppocr/utils/ic15_dict.txt'。
 
 ## 引用
 
diff --git a/doc/doc_en/algorithm_rec_visionlan_en.md b/doc/doc_en/algorithm_rec_visionlan_en.md
index 70c2ccc470af0a03485d9d234e86e384c087617f..cf2293b3d091820d5a91a78834f501f1ac8da9dd 100644
--- a/doc/doc_en/algorithm_rec_visionlan_en.md
+++ b/doc/doc_en/algorithm_rec_visionlan_en.md
@@ -120,7 +120,7 @@ Not supported
 ## 5. FAQ
 
 1. Note that the MJSynth and SynthText datasets come from [VisionLAN repo](https://github.com/wangyuxin87/VisionLAN).
-2. We use the pre-trained model provided by the VisionLAN authors for finetune training.
+2. We use the pre-trained model provided by the VisionLAN authors for finetune training. The dictionary for the pre-trained model is 'ppocr/utils/ic15_dict.txt'.
 
 ## Citation
 
diff --git a/ppocr/data/imaug/label_ops.py b/ppocr/data/imaug/label_ops.py
index 59cb9b8a253cf04244ebf83511ab412174487a53..8191e4c3753a16c9bbff6b98f1f59a64f4b4e0f3 100644
--- a/ppocr/data/imaug/label_ops.py
+++ b/ppocr/data/imaug/label_ops.py
@@ -107,6 +107,7 @@ class BaseRecLabelEncode(object):
         self.beg_str = "sos"
         self.end_str = "eos"
         self.lower = lower
+        self.use_default_dict = False
 
         if character_dict_path is None:
             logger = get_logger()
@@ -116,8 +117,11 @@ class BaseRecLabelEncode(object):
             self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
             dict_character = list(self.character_str)
             self.lower = True
+            self.use_default_dict = True
         else:
             self.character_str = []
+            if 'ppocr/utils/ic15_dict.txt' in character_dict_path:
+                self.use_default_dict = True
             with open(character_dict_path, "rb") as fin:
                 lines = fin.readlines()
                 for line in lines:
@@ -1344,8 +1348,9 @@ class VLLabelEncode(BaseRecLabelEncode):
                  **kwargs):
         super(VLLabelEncode, self).__init__(
             max_text_length, character_dict_path, use_space_char, lower)
-        self.character = self.character[10:] + self.character[
-            1:10] + [self.character[0]]
+        if self.use_default_dict:
+            self.character = self.character[10:] + self.character[
+                1:10] + [self.character[0]]
         self.dict = {}
         for i, char in enumerate(self.character):
             self.dict[char] = i
diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py
index 99e7d0c90f24373c97247bcd407d30af2b48a430..db9e20cbc45774c019784d9f2f19f6c2bb484759 100644
--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@@ -26,10 +26,15 @@ class BaseRecLabelDecode(object):
         self.end_str = "eos"
         self.reverse = False
         self.character_str = []
+        self.use_default_dict = False
+
         if character_dict_path is None:
             self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
             dict_character = list(self.character_str)
+            self.use_default_dict = True
         else:
+            if 'ppocr/utils/ic15_dict.txt' in character_dict_path:
+                self.use_default_dict = True
             with open(character_dict_path, "rb") as fin:
                 lines = fin.readlines()
                 for line in lines:
@@ -720,8 +725,9 @@ class VLLabelDecode(BaseRecLabelDecode):
         super(VLLabelDecode, self).__init__(character_dict_path, use_space_char)
         self.max_text_length = kwargs.get('max_text_length', 25)
         self.nclass = len(self.character) + 1
-        self.character = self.character[10:] + self.character[
-            1:10] + [self.character[0]]
+        if self.use_default_dict:
+            self.character = self.character[10:] + self.character[
+                1:10] + [self.character[0]]
 
     def decode(self, text_index, text_prob=None, is_remove_duplicate=False):
         """ convert text-index into text-label. """