diff --git a/docs/source/cls/custom_dataset.md b/docs/source/cls/custom_dataset.md
index e39dcf12d..b7c06cd7a 100644
--- a/docs/source/cls/custom_dataset.md
+++ b/docs/source/cls/custom_dataset.md
@@ -108,7 +108,7 @@ for epoch in range(1, epochs + 1):
         optimizer.clear_grad()
 
         # Calculate loss
-        avg_loss = loss.numpy()[0]
+        avg_loss = float(loss)
 
         # Calculate metrics
         preds = paddle.argmax(logits, axis=1)
diff --git a/docs/tutorial/cls/cls_tutorial.ipynb b/docs/tutorial/cls/cls_tutorial.ipynb
index 56b488adc..3cee64991 100644
--- a/docs/tutorial/cls/cls_tutorial.ipynb
+++ b/docs/tutorial/cls/cls_tutorial.ipynb
@@ -509,7 +509,7 @@
     "        optimizer.clear_grad()\n",
     "\n",
     "        # Calculate loss\n",
-    "        avg_loss += loss.numpy()[0]\n",
+    "        avg_loss += float(loss)\n",
     "\n",
     "        # Calculate metrics\n",
     "        preds = paddle.argmax(logits, axis=1)\n",
diff --git a/paddlespeech/cls/exps/panns/train.py b/paddlespeech/cls/exps/panns/train.py
index fba38a01c..133893081 100644
--- a/paddlespeech/cls/exps/panns/train.py
+++ b/paddlespeech/cls/exps/panns/train.py
@@ -101,7 +101,7 @@ if __name__ == "__main__":
             optimizer.clear_grad()
 
             # Calculate loss
-            avg_loss += loss.numpy()[0]
+            avg_loss += float(loss)
 
             # Calculate metrics
             preds = paddle.argmax(logits, axis=1)
diff --git a/paddlespeech/kws/exps/mdtc/train.py b/paddlespeech/kws/exps/mdtc/train.py
index 94e45d590..d5bb5e020 100644
--- a/paddlespeech/kws/exps/mdtc/train.py
+++ b/paddlespeech/kws/exps/mdtc/train.py
@@ -110,7 +110,7 @@ if __name__ == '__main__':
             optimizer.clear_grad()
 
             # Calculate loss
-            avg_loss += loss.numpy()[0]
+            avg_loss += float(loss)
 
             # Calculate metrics
             num_corrects += corrects
diff --git a/tests/unit/tts/test_pwg.py b/tests/unit/tts/test_pwg.py
index 78cb34f25..10c82c9fd 100644
--- a/tests/unit/tts/test_pwg.py
+++ b/tests/unit/tts/test_pwg.py
@@ -13,6 +13,7 @@
 # limitations under the License.
 import paddle
 import torch
+from paddle.device.cuda import synchronize
 from parallel_wavegan.layers import residual_block
 from parallel_wavegan.layers import upsample
 from parallel_wavegan.models import parallel_wavegan as pwgan
@@ -24,7 +25,6 @@ from paddlespeech.t2s.models.parallel_wavegan import PWGGenerator
 from paddlespeech.t2s.models.parallel_wavegan import ResidualBlock
 from paddlespeech.t2s.models.parallel_wavegan import ResidualPWGDiscriminator
 from paddlespeech.t2s.utils.layer_tools import summary
-from paddlespeech.t2s.utils.profile import synchronize
 
 paddle.set_device("gpu:0")
 device = torch.device("cuda:0")