diff --git a/demos/speech_ssl/README_cn.md b/demos/speech_ssl/README_cn.md
index a18c778a7..5b209419a 100644
--- a/demos/speech_ssl/README_cn.md
+++ b/demos/speech_ssl/README_cn.md
@@ -56,7 +56,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
 
   # 识别文本
   text = ssl_executor(
-      model='wav2vec2,
+      model='wav2vec2',
       task='asr',
       lang='en',
       sample_rate=16000,
diff --git a/paddlespeech/audio/utils/tensor_utils.py b/paddlespeech/audio/utils/tensor_utils.py
index 93883c94d..43dcac0ac 100644
--- a/paddlespeech/audio/utils/tensor_utils.py
+++ b/paddlespeech/audio/utils/tensor_utils.py
@@ -248,7 +248,7 @@ def st_reverse_pad_list(ys_pad: paddle.Tensor,
     #   >>> tensor([[ 2,  1,  0],
     #   >>>         [ 2,  1,  0],
     #   >>>         [ 0, -1, -2]])
-    index = index * seq_mask
+    index = index * seq_mask.astype(index.dtype)
 
     #   >>> index
     #   >>> tensor([[2, 1, 0],
diff --git a/setup.py b/setup.py
index 48c684855..927f7edb6 100644
--- a/setup.py
+++ b/setup.py
@@ -59,6 +59,7 @@ base = [
     "paddlespeech_feat",
     "praatio>=5.0.0, <=5.1.1",
     "prettytable",
+    "pydantic>=1.10.14, <2.0",
     "pypinyin<=0.44.0",
     "pypinyin-dict",
     "python-dateutil",