diff --git a/README_CN.md b/README_CN.md
index 8bc42e2..704660e 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -54,14 +54,14 @@ Qwen2-Audio 三阶段训练过程概述。
 <b>（注意：我们所展示的评测结果是在原始训练框架的初始模型上的，然而在框架转换 Huggingface 后指标出现了部分波动，在这里我们展示我们的全部测评结果：首先是论文中的初始模型结果）</b>
 
 <table><thead><tr><th rowspan="2">Task</th><th rowspan="2">Dataset</th><th rowspan="2">Model</th><th colspan="2">Performance</th></tr><tr><th>Metrics</th><th>Results</th></tr></thead><tbody><tr><td rowspan="15">ASR</td><td rowspan="7"><b>Librispeech</b><br>dev-clean | dev-other | <br>test-clean | test-other</td><td>SpeechT5</td><td rowspan="7">WER </td><td>2.1 | 5.5 | 2.4 | 5.8</td></tr><tr><td>SpeechNet</td><td>- | - | 30.7 | -</td></tr><tr><td>SLM-FT</td><td>- | - | 2.6 | 5.0</td></tr><tr><td>SALMONN</td><td>- | - | 2.1 | 4.9</td></tr><tr><td>SpeechVerse</td><td>- | - | 2.1 | 4.4</td></tr><tr><td>Qwen-Audio</td><td>1.8 | 4.0 | 2.0 | 4.2</td></tr><tr><td>Qwen2-Audio</td><td><b>1.3 | 3.4 | 1.6 | 3.6</b></td></tr><tr><td rowspan="2"><b>Common Voice 15</b> <br>en | zh | yue | fr</td><td>Whisper-large-v3</td><td rowspan="2">WER </td><td>9.3 | 12.8 | 10.9 | 10.8</td></tr><tr><td>Qwen2-Audio</td><td><b>8.6 | 6.9 | 5.9 | 9.6</b></td></tr>
-<tr><td rowspan="2"><b>Fleurs</b> <br>zh</td><td>Whisper-large-v3</td><td rowspan="2">WER </td><td>7.7</td></tr><tr><td>Qwen2-Audio</td><td><b>7.5</b></td></tr><tr><td rowspan="4"><b>Aishell2</b> <br>Mic | iOS | Android</td><td>MMSpeech-base</td><td rowspan="4">WER </td><td>4.5 | 3.9 | 4.0</td></tr><tr><td>Paraformer-large</td><td>- | <b>2.9</b> | -</td></tr><tr><td>Qwen-Audio</td><td>3.3 | 3.1 | 3.3</td></tr><tr><td>Qwen2-Audio</td><td><b>3.0</b> | 3.0 | <b>2.9</b></td></tr><tr><td rowspan="8">S2TT</td><td rowspan="5"><b>CoVoST2</b> <br>en-de | de-en | <br>en-zh | zh-en</td><td>SALMONN</td><td rowspan="5">BLEU </td><td>18.6 | - | 33.1 | -</td></tr><tr><td>SpeechLLaMA</td><td>- | 27.1 | - | 12.3</td></tr><tr><td>BLSP</td><td>14.1 | - | - | -</td></tr><tr><td>Qwen-Audio</td><td>25.1 | 33.9 | 41.5 | 15.7</td></tr><tr><td>Qwen2-Audio</td><td><b>29.9 | 35.2 | 45.2 | 24.4</b></td></tr>
+<tr><td rowspan="2"><b>Fleurs</b> <br>zh</td><td>Whisper-large-v3</td><td rowspan="2">WER </td><td>7.7</td></tr><tr><td>Qwen2-Audio</td><td><b>7.5</b></td></tr><tr><td rowspan="4"><b>Aishell2</b> <br>Mac | iOS | Android</td><td>MMSpeech-base</td><td rowspan="4">WER </td><td>4.5 | 3.9 | 4.0</td></tr><tr><td>Paraformer-large</td><td>- | <b>2.9</b> | -</td></tr><tr><td>Qwen-Audio</td><td>3.3 | 3.1 | 3.3</td></tr><tr><td>Qwen2-Audio</td><td><b>3.0</b> | 3.0 | <b>2.9</b></td></tr><tr><td rowspan="8">S2TT</td><td rowspan="5"><b>CoVoST2</b> <br>en-de | de-en | <br>en-zh | zh-en</td><td>SALMONN</td><td rowspan="5">BLEU </td><td>18.6 | - | 33.1 | -</td></tr><tr><td>SpeechLLaMA</td><td>- | 27.1 | - | 12.3</td></tr><tr><td>BLSP</td><td>14.1 | - | - | -</td></tr><tr><td>Qwen-Audio</td><td>25.1 | 33.9 | 41.5 | 15.7</td></tr><tr><td>Qwen2-Audio</td><td><b>29.9 | 35.2 | 45.2 | 24.4</b></td></tr>
 <tr><td rowspan="3"><b>CoVoST2</b> <br>es-en | fr-en | it-en |</td><td>SpeechLLaMA</td><td rowspan="3">BLEU </td><td>27.9 | 25.2 | 25.9</td></tr><tr><td>Qwen-Audio</td><td>39.7 | <b>38.5</b> | 36.0</td></tr><tr><td>Qwen2-Audio</td><td><b>40.0 | 38.5 | 36.3</b></td></tr><tr><td rowspan="3">SER</td><td rowspan="3"><b>Meld</b></td><td>WavLM-large</td><td rowspan="3">ACC </td><td>0.542</td></tr><tr><td>Qwen-Audio</td><td><b>0.557</b></td></tr><tr><td>Qwen2-Audio</td><td>0.553</td></tr><tr><td rowspan="4">VSC</td><td rowspan="4"><b>VocalSound</b></td><td>CLAP</td><td rowspan="4">ACC </td><td>0.4945</td></tr><tr><td>Pengi</td><td>0.6035</td></tr><tr><td>Qwen-Audio</td><td>0.9289</td></tr><tr><td>Qwen2-Audio</td><td><b>0.9392</b></td></tr>
 <tr><td>AIR-Bench <br></td><td><b>Chat Benchmark</b><br>Speech | Sound |<br> Music | Mixed-Audio</td><td>SALMONN<br>BLSP<br>Pandagpt<br>Macaw-LLM<br>SpeechGPT<br>Next-gpt<br>Qwen-Audio<br>Gemini-1.5-pro<br>Qwen2-Audio</td><td>GPT-4 </td><td>6.16 | 6.28 | 5.95 | 6.08<br>6.17 | 5.55 | 5.08 | 5.33<br>3.58 | 5.46 | 5.06 | 4.25<br>0.97 | 1.01 | 0.91 | 1.01<br>1.57 | 0.95 | 0.95 | 4.13<br>3.86 | 4.76 | 4.18 | 4.13<br>6.47 | 6.95 | 5.52 | 6.08<br>6.97 | 5.49 | 5.06 | 5.27<br><b>7.18 | 6.99 | 6.79 | 6.77</b></td></tr></tbody></table>
 
 <b>（其次是转换 huggingface 后的）</b>
 
 <table><thead><tr><th rowspan="2">Task</th><th rowspan="2">Dataset</th><th rowspan="2">Model</th><th colspan="2">Performance</th></tr><tr><th>Metrics</th><th>Results</th></tr></thead><tbody><tr><td rowspan="15">ASR</td><td rowspan="7"><b>Librispeech</b><br>dev-clean | dev-other | <br>test-clean | test-other</td><td>SpeechT5</td><td rowspan="7">WER </td><td>2.1 | 5.5 | 2.4 | 5.8</td></tr><tr><td>SpeechNet</td><td>- | - | 30.7 | -</td></tr><tr><td>SLM-FT</td><td>- | - | 2.6 | 5.0</td></tr><tr><td>SALMONN</td><td>- | - | 2.1 | 4.9</td></tr><tr><td>SpeechVerse</td><td>- | - | 2.1 | 4.4</td></tr><tr><td>Qwen-Audio</td><td>1.8 | 4.0 | 2.0 | 4.2</td></tr><tr><td>Qwen2-Audio</td><td><b>1.7 | 3.6 | 1.7 | 4.0</b></td></tr><tr><td rowspan="2"><b>Common Voice 15</b> <br>en | zh | yue | fr</td><td>Whisper-large-v3</td><td rowspan="2">WER </td><td>9.3 | 12.8 | 10.9 | 10.8</td></tr><tr><td>Qwen2-Audio</td><td><b>8.7 | 6.5 | 5.9 | 9.6</b></td></tr>
-<tr><td rowspan="2"><b>Fleurs</b> <br>zh</td><td>Whisper-large-v3</td><td rowspan="2">WER </td><td>7.7</td></tr><tr><td>Qwen2-Audio</td><td><b>7.0</b></td></tr><tr><td rowspan="4"><b>Aishell2</b> <br>Mic | iOS | Android</td><td>MMSpeech-base</td><td rowspan="4">WER </td><td>4.5 | 3.9 | 4.0</td></tr><tr><td>Paraformer-large</td><td>- | <b>2.9</b> | -</td></tr><tr><td>Qwen-Audio</td><td>3.3 | 3.1 | 3.3</td></tr><tr><td>Qwen2-Audio</td><td><b>3.2</b> | 3.1 | <b>2.9</b></td></tr><tr><td rowspan="8">S2TT</td><td rowspan="5"><b>CoVoST2</b> <br>en-de | de-en | <br>en-zh | zh-en</td><td>SALMONN</td><td rowspan="5">BLEU </td><td>18.6 | - | 33.1 | -</td></tr><tr><td>SpeechLLaMA</td><td>- | 27.1 | - | 12.3</td></tr><tr><td>BLSP</td><td>14.1 | - | - | -</td></tr><tr><td>Qwen-Audio</td><td>25.1 | <b>33.9</b> | 41.5 | 15.7</td></tr><tr><td>Qwen2-Audio</td><td><b>29.6</b> | 33.6 | <b>45.6</b> | <b>24.0</b></td></tr>
+<tr><td rowspan="2"><b>Fleurs</b> <br>zh</td><td>Whisper-large-v3</td><td rowspan="2">WER </td><td>7.7</td></tr><tr><td>Qwen2-Audio</td><td><b>7.0</b></td></tr><tr><td rowspan="4"><b>Aishell2</b> <br>Mac | iOS | Android</td><td>MMSpeech-base</td><td rowspan="4">WER </td><td>4.5 | 3.9 | 4.0</td></tr><tr><td>Paraformer-large</td><td>- | <b>2.9</b> | -</td></tr><tr><td>Qwen-Audio</td><td>3.3 | 3.1 | 3.3</td></tr><tr><td>Qwen2-Audio</td><td><b>3.2</b> | 3.1 | <b>2.9</b></td></tr><tr><td rowspan="8">S2TT</td><td rowspan="5"><b>CoVoST2</b> <br>en-de | de-en | <br>en-zh | zh-en</td><td>SALMONN</td><td rowspan="5">BLEU </td><td>18.6 | - | 33.1 | -</td></tr><tr><td>SpeechLLaMA</td><td>- | 27.1 | - | 12.3</td></tr><tr><td>BLSP</td><td>14.1 | - | - | -</td></tr><tr><td>Qwen-Audio</td><td>25.1 | <b>33.9</b> | 41.5 | 15.7</td></tr><tr><td>Qwen2-Audio</td><td><b>29.6</b> | 33.6 | <b>45.6</b> | <b>24.0</b></td></tr>
 <tr><td rowspan="3"><b>CoVoST2</b> <br>es-en | fr-en | it-en |</td><td>SpeechLLaMA</td><td rowspan="3">BLEU </td><td>27.9 | 25.2 | 25.9</td></tr><tr><td>Qwen-Audio</td><td><b>39.7 | 38.5 | 36.0</b></td></tr><tr><td>Qwen2-Audio</td><td>38.7 | 37.2 | 35.2</td></tr><tr><td rowspan="3">SER</td><td rowspan="3"><b>Meld</b></td><td>WavLM-large</td><td rowspan="3">ACC </td><td>0.542</td></tr><tr><td>Qwen-Audio</td><td><b>0.557</b></td></tr><tr><td>Qwen2-Audio</td><td>0.535</td></tr><tr><td rowspan="4">VSC</td><td rowspan="4"><b>VocalSound</b></td><td>CLAP</td><td rowspan="4">ACC </td><td>0.4945</td></tr><tr><td>Pengi</td><td>0.6035</td></tr><tr><td>Qwen-Audio</td><td>0.9289</td></tr><tr><td>Qwen2-Audio</td><td><b>0.9395</b></td></tr>
 <tr><td>AIR-Bench <br></td><td><b>Chat Benchmark</b><br>Speech | Sound |<br> Music | Mixed-Audio</td><td>SALMONN<br>BLSP<br>Pandagpt<br>Macaw-LLM<br>SpeechGPT<br>Next-gpt<br>Qwen-Audio<br>Gemini-1.5-pro<br>Qwen2-Audio</td><td>GPT-4 </td><td>6.16 | 6.28 | 5.95 | 6.08<br>6.17 | 5.55 | 5.08 | 5.33<br>3.58 | 5.46 | 5.06 | 4.25<br>0.97 | 1.01 | 0.91 | 1.01<br>1.57 | 0.95 | 0.95 | 4.13<br>3.86 | 4.76 | 4.18 | 4.13<br>6.47 | <b>6.95</b> | 5.52 | 6.08<br>6.97 | 5.49 | 5.06 | 5.27<br><b>7.24</b> | 6.83 | <b>6.73</b> | <b>6.42</b></td></tr></tbody></table>