Merge pull request #1498 from xinnan-tech/py_Text

update:优化空asr语音

main/xiaozhi-server/core/handle/helloHandle.py

@@ -17,7 +17,7 @@ TAG = __name__
 
 WAKEUP_CONFIG = {
     "refresh_time": 5,
-    "words": ["你好小智", "你好啊小智", "小智你好", "小智"],
+    "words": ["你好", "你好啊", "嘿，你好", "嗨"],
 }
 
 # 创建全局的唤醒词配置管理器

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -15,11 +15,13 @@ async def handleAudioMessage(conn, audio):
     have_voice = conn.vad.is_vad(conn, audio)
 
     # 如果设备刚刚被唤醒，短暂忽略VAD检测
-    if hasattr(conn, "just_woken_up") and conn.just_woken_up:
+    if have_voice and hasattr(conn, "just_woken_up") and conn.just_woken_up:
         have_voice = False
         # 设置一个短暂延迟后恢复VAD检测
         conn.asr_audio.clear()
-        asyncio.create_task(resume_vad_detection(conn))
+        if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
+            print("clear asr_audio")
+            conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
 
     if have_voice:
         if conn.client_is_speaking:
@@ -32,7 +34,7 @@ async def handleAudioMessage(conn, audio):
 
 async def resume_vad_detection(conn):
     # 等待2秒后恢复VAD检测
-    await asyncio.sleep(2)
+    await asyncio.sleep(1)
     conn.just_woken_up = False
 
 

main/xiaozhi-server/core/providers/asr/doubao.py

@@ -168,6 +168,7 @@ class ASRProvider(ASRProviderBase):
                 if (
                     "payload_msg" in result
                     and result["payload_msg"]["code"] != self.success_code
+                    and result["payload_msg"]["code"] != 1013  # 忽略无有效语音的错误
                 ):
                     logger.bind(tag=TAG).error(f"ASR error: {result}")
                     return None
@@ -203,6 +204,9 @@ class ASRProvider(ASRProviderBase):
                     if len(result["payload_msg"]["result"]) > 0:
                         return result["payload_msg"]["result"][0]["text"]
                     return None
+                elif "payload_msg" in result and result["payload_msg"]["code"] == 1013:
+                    # 无有效语音，返回空字符串
+                    return ""
                 else:
                     logger.bind(tag=TAG).error(f"ASR error: {result}")
                     return None

main/xiaozhi-server/core/providers/asr/doubao_stream.py

@@ -157,6 +157,11 @@ class ASRProvider(ASRProviderBase):
 
                     if "payload_msg" in result:
                         payload = result["payload_msg"]
+                        # 检查是否是错误码1013（无有效语音）
+                        if "code" in payload and payload["code"] == 1013:
+                            # 静默处理，不记录错误日志
+                            continue
+
                         if "result" in payload:
                             utterances = payload["result"].get("utterances", [])
                             # 检查duration和空文本的情况