diff --git a/python-package/README.md b/python-package/README.md
index 69c199b56..063adf903 100644
--- a/python-package/README.md
+++ b/python-package/README.md
@@ -14,7 +14,7 @@ For ``insightface<=0.1.5``, we use MXNet as inference backend.
 
 Starting from insightface>=0.2, we use onnxruntime as inference backend.
 
-You have to install ``onnxruntime-gpu`` manually to enable GPU inference, or install ``onnxruntime`` to use CPU only inference.
+You have to install ``onnxruntime-gpu`` manually to enable GPU inference, install ``onnxruntime-cann`` manually to enable Ascend NPU inference, or install ``onnxruntime`` to use CPU only inference.
 
 ## Change Log
 
diff --git a/python-package/insightface/model_zoo/model_zoo.py b/python-package/insightface/model_zoo/model_zoo.py
index fc6283114..11938ec9f 100644
--- a/python-package/insightface/model_zoo/model_zoo.py
+++ b/python-package/insightface/model_zoo/model_zoo.py
@@ -8,6 +8,7 @@
 import os.path as osp
 import glob
 import onnxruntime
+import importlib
 from .arcface_onnx import *
 from .retinaface import *
 #from .scrfd import *
@@ -68,7 +69,12 @@ def find_onnx_file(dir_path):
     return paths[-1]
 
 def get_default_providers():
-    return ['CUDAExecutionProvider', 'CPUExecutionProvider']
+    # In Ascend NPU, acl is a base module, if the module `acl` exists, the codes runs in Ascend device.
+    if importlib.util.find_spec("acl") is not None:
+        providers = ["CANNExecutionProvider","CPUExecutionProvider"]
+    else:
+        providers = ['CUDAExecutionProvider', 'CPUExecutionProvider']
+    return providers
 
 def get_default_provider_options():
     return None