fix:修复FunASR多设备连接时声纹识别配置相互覆盖的问题

main/xiaozhi-server/core/connection.py

@@ -24,7 +24,6 @@ from core.utils.modules_initialize import (
     initialize_asr,
 )
 from core.handle.reportHandle import report
-from core.utils.modules_initialize import initialize_voiceprint
 from core.providers.tts.default import DefaultTTS
 from concurrent.futures import ThreadPoolExecutor
 from core.utils.dialogue import Message, Dialogue
@@ -39,6 +38,7 @@ from core.providers.tts.dto.dto import ContentType, TTSMessageDTO, SentenceType
 from config.logger import setup_logging, build_module_string, create_connection_logger
 from config.manage_api_client import DeviceNotFoundException, DeviceBindException
 from core.utils.prompt_manager import PromptManager
+from core.utils.voiceprint_provider import VoiceprintProvider
 
 
 TAG = __name__
@@ -109,6 +109,9 @@ class ConnectionHandler:
         self.memory = _memory
         self.intent = _intent
 
+        # 为每个连接单独管理声纹识别
+        self.voiceprint_provider = None
+
         # vad相关变量
         self.client_audio_buffer = bytearray()
         self.client_have_voice = False
@@ -348,14 +351,10 @@ class ConnectionHandler:
                 self.vad = self._vad
             if self.asr is None:
                 self.asr = self._initialize_asr()
-            try:
+            
-                success = initialize_voiceprint(self.asr, self.config)
+            # 初始化声纹识别
-                if success:
+            self._initialize_voiceprint()
-                    self.logger.bind(tag=TAG).info("声纹识别功能已在连接时动态启用")
+            
-                else:
-                    self.logger.bind(tag=TAG).info("声纹识别功能未启用或配置不完整")
-            except Exception as e:
-                self.logger.bind(tag=TAG).warning(f"声纹识别初始化失败: {str(e)}")
             # 打开语音识别通道
             asyncio.run_coroutine_threadsafe(
                 self.asr.open_audio_channels(self), self.loop
@@ -426,6 +425,18 @@ class ConnectionHandler:
 
         return asr
 
+    def _initialize_voiceprint(self):
+        """为当前连接初始化声纹识别"""
+        try:
+            voiceprint_config = self.config.get("voiceprint", {})
+            if voiceprint_config:
+                self.voiceprint_provider = VoiceprintProvider(voiceprint_config)
+                self.logger.bind(tag=TAG).info("声纹识别功能已在连接时动态启用")
+            else:
+                self.logger.bind(tag=TAG).info("声纹识别功能未启用或配置不完整")
+        except Exception as e:
+            self.logger.bind(tag=TAG).warning(f"声纹识别初始化失败: {str(e)}")
+
     def _initialize_private_config(self):
         """如果是从配置文件获取，则进行二次实例化"""
         if not self.read_config_from_api:

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

@@ -17,7 +17,6 @@ from core.handle.receiveAudioHandle import startToChat
 from core.handle.reportHandle import enqueue_asr_report
 from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import handleAudioMessage
-from core.utils.voiceprint_provider import VoiceprintProvider
 
 TAG = __name__
 logger = setup_logging()
@@ -25,13 +24,7 @@ logger = setup_logging()
 
 class ASRProviderBase(ABC):
     def __init__(self):
-        self.voiceprint_provider = None
+        pass  # 将声纹识别从ASR实例分离，移到连接级别管理
-
-    def init_voiceprint(self, voiceprint_config: dict):
-        """初始化声纹识别"""
-        if voiceprint_config:
-            self.voiceprint_provider = VoiceprintProvider(voiceprint_config)
-            logger.bind(tag=TAG).info("声纹识别模块已初始化")
 
     # 打开音频通道
     async def open_audio_channels(self, conn):
@@ -94,7 +87,8 @@ class ASRProviderBase(ABC):
             
             # 预先准备WAV数据
             wav_data = None
-            if self.voiceprint_provider and combined_pcm_data:
+            # 使用连接的声纹识别提供者
+            if conn.voiceprint_provider and combined_pcm_data:
                 wav_data = self._pcm_to_wav(combined_pcm_data)
             
             
@@ -129,8 +123,9 @@ class ASRProviderBase(ABC):
                     loop = asyncio.new_event_loop()
                     asyncio.set_event_loop(loop)
                     try:
+                        # 使用连接的声纹识别提供者
                         result = loop.run_until_complete(
-                            self.voiceprint_provider.identify_speaker(wav_data, conn.session_id)
+                            conn.voiceprint_provider.identify_speaker(wav_data, conn.session_id)
                         )
                         return result
                     finally:
@@ -145,7 +140,7 @@ class ASRProviderBase(ABC):
             with concurrent.futures.ThreadPoolExecutor(max_workers=2) as thread_executor:
                 asr_future = thread_executor.submit(run_asr)
                 
-                if self.voiceprint_provider and wav_data:
+                if conn.voiceprint_provider and wav_data:
                     voiceprint_future = thread_executor.submit(run_voiceprint)
                     
                     # 等待两个线程都完成