diff --git a/README.md b/README.md
index 46345ae..dccf141 100644
--- a/README.md
+++ b/README.md
@@ -50,7 +50,7 @@ Model Zoo:
 We compared the performance of multilingual speech recognition between SenseVoice and Whisper on open-source benchmark datasets, including AISHELL-1, AISHELL-2, Wenetspeech, LibriSpeech, and Common Voice. n terms of Chinese and Cantonese recognition, the SenseVoice-Small model has advantages.
 
 <div align="center">  
-<img src="image/asr_results.png" width="1000" />
+<img src="image/asr_results1.png" width="500" /><img src="image/asr_results2.png" width="500" />
 </div>
 
 ## Speech Emotion Recognition
diff --git a/README_zh.md b/README_zh.md
index c87aa32..859b33c 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -50,7 +50,7 @@ SenseVoice是具有音频理解能力的音频基础模型，包括语音识别
 我们在开源基准数据集（包括 AISHELL-1、AISHELL-2、Wenetspeech、Librispeech和Common Voice）上比较了SenseVoice与Whisper的多语言语音识别性能和推理效率。在中文和粤语识别效果上，SenseVoice-Small模型具有明显的效果优势。
 
 <div align="center">  
-<img src="image/asr_results.png" width="1000" />
+<img src="image/asr_results1.png" width="500" /><img src="image/asr_results2.png" width="500" />
 </div>
 
 ## 情感识别
diff --git a/image/asr_results1.png b/image/asr_results1.png
new file mode 100644
index 0000000..402581e
Binary files /dev/null and b/image/asr_results1.png differ
diff --git a/image/asr_results2.png b/image/asr_results2.png
new file mode 100644
index 0000000..4645703
Binary files /dev/null and b/image/asr_results2.png differ