fix: asr识别缺字现象，去除无用的变量

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

@@ -1,5 +1,4 @@
 import time
-import asyncio
 import json
 from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
@@ -14,14 +13,6 @@ TAG = __name__
 async def handleAudioMessage(conn, audio):
     # 当前片段是否有人说话
     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 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()
-        if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
-            conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
-        return
 
     if have_voice:
         if conn.client_is_speaking:
@@ -31,13 +22,6 @@ async def handleAudioMessage(conn, audio):
     # 接收音频
     await conn.asr.receive_audio(conn, audio, have_voice)
 
-
-async def resume_vad_detection(conn):
-    # 等待2秒后恢复VAD检测
-    await asyncio.sleep(1)
-    conn.just_woken_up = False
-
-
 async def startToChat(conn, text):
     # 检查输入是否是JSON格式（包含说话人信息）
     speaker_name = None

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

@@ -12,7 +12,7 @@ import time
 import concurrent.futures
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
-from typing import Optional, Tuple, List, Dict, Any
+from typing import Optional, Tuple, List
 from core.handle.receiveAudioHandle import startToChat
 from core.handle.reportHandle import enqueue_asr_report
 from core.utils.util import remove_punctuation_and_length
@@ -132,8 +132,6 @@ class ASRProviderBase(ABC):
                     return None
             
             # 使用线程池执行器并行运行
-            parallel_start_time = time.monotonic()
-            
             with concurrent.futures.ThreadPoolExecutor(max_workers=2) as thread_executor:
                 asr_future = thread_executor.submit(run_asr)
                 

main/xiaozhi-server/core/providers/vad/silero.py

@@ -33,8 +33,8 @@ class VADProvider(VADProviderBase):
             int(min_silence_duration_ms) if min_silence_duration_ms else 1000
         )
 
-        # 至少要多少帧才算有语音
-        self.frame_window_threshold = 3
+        # 至少要多少帧才算有语音,增加灵敏度
+        self.frame_window_threshold = 1
 
     def is_vad(self, conn, opus_packet):
         try: