fix: 音频影响线程问题

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

@@ -9,7 +9,6 @@ import asyncio
 import traceback
 import threading
 import opuslib_next
-import concurrent.futures
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
 from typing import Optional, Tuple, List
@@ -94,66 +93,31 @@ class ASRProviderBase(ABC):
                 wav_data = self._pcm_to_wav(combined_pcm_data)
 
             # 定义ASR任务
-            def run_asr():
+            asr_task = self.speech_to_text(asr_audio_task, conn.session_id, conn.audio_format)
-                start_time = time.monotonic()
-                try:
-                    loop = asyncio.new_event_loop()
-                    asyncio.set_event_loop(loop)
-                    try:
-                        result = loop.run_until_complete(
-                            self.speech_to_text(asr_audio_task, conn.session_id, conn.audio_format)
-                        )
-                        end_time = time.monotonic()
-                        logger.bind(tag=TAG).debug(f"ASR耗时: {end_time - start_time:.3f}s")
-                        return result
-                    finally:
-                        loop.close()
-                except Exception as e:
-                    end_time = time.monotonic()
-                    logger.bind(tag=TAG).error(f"ASR失败: {e}")
-                    return ("", None)
 
-            # 定义声纹识别任务
+            if conn.voiceprint_provider and wav_data:
-            def run_voiceprint():
+                voiceprint_task = conn.voiceprint_provider.identify_speaker(wav_data, conn.session_id)
-                if not wav_data:
+                # 并发等待两个结果
-                    return None
+                asr_result, voiceprint_result = await asyncio.gather(
-                try:
+                    asr_task, voiceprint_task, return_exceptions=True
-                    loop = asyncio.new_event_loop()
+                )
-                    asyncio.set_event_loop(loop)
+            else:
-                    try:
+                asr_result = await asr_task
-                        # 使用连接的声纹识别提供者
+                voiceprint_result = None
-                        result = loop.run_until_complete(
-                            conn.voiceprint_provider.identify_speaker(wav_data, conn.session_id)
-                        )
-                        return result
-                    finally:
-                        loop.close()
-                except Exception as e:
-                    logger.bind(tag=TAG).error(f"声纹识别失败: {e}")
-                    return None
 
-            # 使用线程池执行器并行运行
+            # 记录识别结果 - 检查是否为异常
-            with concurrent.futures.ThreadPoolExecutor(max_workers=2) as thread_executor:
+            if isinstance(asr_result, Exception):
-                asr_future = thread_executor.submit(run_asr)
+                logger.bind(tag=TAG).error(f"ASR识别失败: {asr_result}")
+                raw_text = ""
+            else:
+                raw_text, _ = asr_result
 
-                if conn.voiceprint_provider and wav_data:
+            if isinstance(voiceprint_result, Exception):
-                    voiceprint_future = thread_executor.submit(run_voiceprint)
+                logger.bind(tag=TAG).error(f"声纹识别失败: {voiceprint_result}")
+                speaker_name = ""
+            else:
+                speaker_name = voiceprint_result
 
-                    # 等待两个线程都完成
-                    asr_result = asr_future.result(timeout=15)
-                    voiceprint_result = voiceprint_future.result(timeout=15)
-                    
-                    results = {"asr": asr_result, "voiceprint": voiceprint_result}
-                else:
-                    asr_result = asr_future.result(timeout=15)
-                    results = {"asr": asr_result, "voiceprint": None}
-            
-            
-            # 处理结果
-            raw_text, _ = results.get("asr", ("", None))
-            speaker_name = results.get("voiceprint", None)
-            
-            # 记录识别结果
             if raw_text:
                 logger.bind(tag=TAG).info(f"识别文本: {raw_text}")
             if speaker_name: