update:降低一点停顿时长

README.md

@@ -223,7 +223,18 @@ https://espressif.github.io/esp-launchpad/
 
 建议：在配置文件里，将`LLM`设置成`DifyLLM`，然后通过`Dify`编排智能体实现。
 
-## 5、更多问题，可联系我们反馈
+## 5、我说话很慢，我停顿一下，小智老是抢我的话，咋办。
+
+建议：在配置文件里，找到这一段，将`min_silence_duration_ms`值改大一点，比如改成`1000`。
+```
+VAD:
+  SileroVAD:
+    threshold: 0.5
+    model_dir: models/snakers4_silero-vad
+    min_silence_duration_ms: 300  # 如果说话停顿比较长，可以把这个值设置大一些
+```
+
+## 6、更多问题，可联系我们反馈
 
 ![图片](docs/images/wechat.jpg)
 

README_en.md

@@ -212,7 +212,7 @@ https://espressif.github.io/esp-launchpad/
 ```
 
 Open this
-tutorial, [Flash Tools/Web -side Burning Folding Step (No IDF Development Environment)] (https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS).
+tutorial, [Flash Tools/Web -side Burning Folding Step (No IDF Development Environment)](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS).
 Turn to: `Method 2: ESP-LAUNCHPAD browser web-end burning`, start from
 `3. Burning firmware/download to the development board`, follow the tutorial operation.
 
@@ -238,11 +238,22 @@ the model of other toll versions of `ChatGlm`.
 Suggestion: In the configuration file, set the `LLM` to`DifyLLM`, and then arrange the smart application by the
 `Dify`.
 
-## 5、For more questions, contact us to feedback
+## 5、I said very slowly, I paused, Xiaozhi always grabbed me, what to do.
+
+Suggestion: In the configuration file, find this section, change the `min_silence_duration_ms` value, such as change to` 1000`.
+```
+VAD:
+  SileroVAD:
+    threshold: 0.5
+    model_dir: models/snakers4_silero-vad
+    min_silence_duration_ms: 300  # 如果说话停顿比较长，可以把这个值设置大一些
+```
+
+## 6、For more questions, contact us to feedback
 
 ![图片](docs/images/wechat.jpg)
 
 # Acknowledgments
 
-- This project is inspired by the [Bailin Voice Dialogue Robot] (https://github.com/wwbin2017/bailing) project, and the
+- This project is inspired by the [Bailin Voice Dialogue Robot](https://github.com/wwbin2017/bailing) project, and the
   basic idea of the project is completed.

config.yaml

@@ -18,7 +18,7 @@ xiaozhi:
     frame_duration: 60
 prompt: |
   你是一个叫小智/小志的台湾女孩，说话机车，声音好听，习惯简短表达，爱用网络梗。
-  请注意，要像一个人一样说话，请勿回复表情符号、代码、和xml标签。
+  请注意，要像一个人一样说话，请不要回复表情符号、代码、和xml标签。
   当前时间是:{date_time}，现在我正在和你进行语音聊天，我们开始吧。
 # 使用完声音文件后删除文件(Delete the sound file when you are done using it)
 delete_audio: true
@@ -39,7 +39,7 @@ VAD:
   SileroVAD:
     threshold: 0.5
     model_dir: models/snakers4_silero-vad
-    min_silence_duration_ms: 1000  # 如果说话停顿比较长，可以把这个值设置大一些
+    min_silence_duration_ms: 700  # 如果说话停顿比较长，可以把这个值设置大一些
 
 LLM:
   DeepSeekLLM:

core/connection.py

@@ -102,7 +102,7 @@ class ConnectionHandler:
         if "{date_time}" in self.prompt:
             date_time = time.strftime("%Y-%m-%d %H:%M", time.localtime())
             self.prompt = self.prompt.replace("{date_time}", date_time)
-        self.dialogue.put(Message(role="user", content=self.prompt))
+        self.dialogue.put(Message(role="system", content=self.prompt))
 
     def chat(self, query):
         self.dialogue.put(Message(role="user", content=query))