diff --git a/docs/source/released_model.md b/docs/source/released_model.md
index 03805b2be6a8ccb4b7e7b364588386a51f585907..87619a558d60eba8d28b2105464680d8cf981d7e 100644
--- a/docs/source/released_model.md
+++ b/docs/source/released_model.md
@@ -1,5 +1,7 @@
 # Released Models
 
+> !!! Since PaddlePaddle support 0-D tensor from 2.5.0, PaddleSpeech Static model will not work for it, please re-export static model.
+
 ## Speech-to-Text Models
 
 ### Speech Recognition Model