diff --git a/docs/source/released_model.md b/docs/source/released_model.md
index cec6b76d6e9a4aff84c3600192270582ff6f27d5..9db6a4c449a67a5ce6207a2f29ffa65ead6d527f 100644
--- a/docs/source/released_model.md
+++ b/docs/source/released_model.md
@@ -66,8 +66,8 @@ GE2E + FastSpeech2 | AISHELL-3  |[ge2e-fastspeech2-aishell3](https://github.com/
 
 Model Type | Dataset| Example Link | Pretrained Models
 :-------------:| :------------:| :-----: | :-----:
-PANN | Audioset| [audioset_tagging_cnn](https://github.com/qiuqiangkong/audioset_tagging_cnn) | [panns_cnn6.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn6.pdparams),[panns_cnn10.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn10.pdparams),[panns_cnn14.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn14.pdparams)
-PANN | ESC-50 |[pann-esc50]("./examples/esc50/cls0")|[panns_cnn6.tar.gz](https://paddlespeech.bj.bcebos.com/cls/panns_cnn6.tar.gz), [panns_cnn10](https://paddlespeech.bj.bcebos.com/cls/panns_cnn10.tar.gz), [panns_cnn14.tar.gz](https://paddlespeech.bj.bcebos.com/cls/panns_cnn14.tar.gz)
+PANN | Audioset| [audioset_tagging_cnn](https://github.com/qiuqiangkong/audioset_tagging_cnn) | [panns_cnn6.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn6.pdparams), [panns_cnn10.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn10.pdparams), [panns_cnn14.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn14.pdparams)
+PANN | ESC-50 |[pann-esc50]("./examples/esc50/cls0")|[esc50_cnn6.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn6.tar.gz), [esc50_cnn10.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn10.tar.gz), [esc50_cnn14.tar.gz](https://paddlespeech.bj.bcebos.com/cls/esc50/esc50_cnn14.tar.gz)
 
 ## Speech Recognition Model  from paddle 1.8
 
diff --git a/examples/esc50/README.md b/examples/esc50/README.md
index 20fecf0c1b455ae1d705ded7024496a923e998ec..2ce57ae0641fad36132bd26e49f867e279a48a9c 100644
--- a/examples/esc50/README.md
+++ b/examples/esc50/README.md
@@ -27,7 +27,9 @@ PaddleAudio提供了PANNs的CNN14、CNN10和CNN6的预训练模型，可供用
 
 |Model|Acc|
 |--|--|
-|CNN14| 0.950
+|CNN14| 0.9500
+|CNN10| 0.8975
+|CNN6| 0.8825
 
 ## 快速开始
 
diff --git a/examples/esc50/RESULTS.md b/examples/esc50/RESULTS.md
new file mode 100644
index 0000000000000000000000000000000000000000..edbf07a3ffcef269f9e4a93cb58995d0b2788abd
--- /dev/null
+++ b/examples/esc50/RESULTS.md
@@ -0,0 +1,9 @@
+## Metrics
+
+5-fold cross validation accuracy on [ESC-50](https://github.com/karolpiczak/ESC-50) dataset:
+
+|Model|Acc|
+|--|--|
+|CNN14| 0.9500
+|CNN10| 0.8975
+|CNN6| 0.8825