Merge branch 'main' into py_MinmaxStreamTTS_test

2026-07-29 10:13:55 +08:00 · 2025-09-09 13:17:09 +08:00
parent 6bc64aa4aa ddd63f4136
commit c3c65708e0
10 changed files with 221 additions and 16 deletions
@@ -432,10 +432,14 @@ class ConnectionHandler:
        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")
+                voiceprint_provider = VoiceprintProvider(voiceprint_config)
+                if voiceprint_provider is not None and voiceprint_provider.enabled:
+                    self.voiceprint_provider = voiceprint_provider
+                    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).warning("声纹识别功能启用但配置不完整")
            else:
-                self.logger.bind(tag=TAG).info("声纹识别功能未启用或配置不完整")
+                self.logger.bind(tag=TAG).info("声纹识别功能未启用")
        except Exception as e:
            self.logger.bind(tag=TAG).warning(f"声纹识别初始化失败: {str(e)}")

@@ -0,0 +1,114 @@
+import os
+import json
+import time
+from typing import Optional, Tuple, List
+from .base import ASRProviderBase
+from config.logger import setup_logging
+from core.providers.asr.dto.dto import InterfaceType
+import vosk
+
+TAG = __name__
+logger = setup_logging()
+
+class ASRProvider(ASRProviderBase):
+    def __init__(self, config: dict, delete_audio_file: bool = True):
+        super().__init__()
+        self.interface_type = InterfaceType.LOCAL
+        self.model_path = config.get("model_path")
+        self.output_dir = config.get("output_dir", "tmp/")
+        self.delete_audio_file = delete_audio_file
+        
+        # 初始化VOSK模型
+        self.model = None
+        self.recognizer = None
+        self._load_model()
+        
+        # 确保输出目录存在
+        os.makedirs(self.output_dir, exist_ok=True)
+
+    def _load_model(self):
+        """加载VOSK模型"""
+        try:
+            if not os.path.exists(self.model_path):
+                raise FileNotFoundError(f"VOSK模型路径不存在: {self.model_path}")
+                
+            logger.bind(tag=TAG).info(f"正在加载VOSK模型: {self.model_path}")
+            self.model = vosk.Model(self.model_path)
+
+            # 初始化VOSK识别器（采样率必须为16kHz）
+            self.recognizer = vosk.KaldiRecognizer(self.model, 16000)
+
+            logger.bind(tag=TAG).info("VOSK模型加载成功")
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"加载VOSK模型失败: {e}")
+            raise
+
+    async def speech_to_text(
+        self, audio_data: List[bytes], session_id: str, audio_format: str = "opus"
+    ) -> Tuple[Optional[str], Optional[str]]:
+        """将语音数据转换为文本"""
+        file_path = None
+        try:
+            # 检查模型是否加载成功
+            if not self.model:
+                logger.bind(tag=TAG).error("VOSK模型未加载，无法进行识别")
+                return "", None
+
+            # 解码音频（如果原始格式是Opus）
+            if audio_format == "pcm":
+                pcm_data = audio_data
+            else:
+                pcm_data = self.decode_opus(audio_data)
+                
+            if not pcm_data:
+                logger.bind(tag=TAG).warning("解码后的PCM数据为空，无法进行识别")
+                return "", None
+                
+            # 合并PCM数据
+            combined_pcm_data = b"".join(pcm_data)
+            if len(combined_pcm_data) == 0:
+                logger.bind(tag=TAG).warning("合并后的PCM数据为空")
+                return "", None
+
+            # 判断是否保存为WAV文件
+            if not self.delete_audio_file:
+                file_path = self.save_audio_to_file(pcm_data, session_id)
+
+            start_time = time.time()
+            
+            
+            # 进行识别（VOSK推荐每次送入2000字节的数据）
+            chunk_size = 2000
+            text_result = ""
+            
+            for i in range(0, len(combined_pcm_data), chunk_size):
+                chunk = combined_pcm_data[i:i+chunk_size]
+                if self.recognizer.AcceptWaveform(chunk):
+                    result = json.loads(self.recognizer.Result())
+                    text = result.get('text', '')
+                    if text:
+                        text_result += text + " "
+            
+            # 获取最终结果
+            final_result = json.loads(self.recognizer.FinalResult())
+            final_text = final_result.get('text', '')
+            if final_text:
+                text_result += final_text
+            
+            logger.bind(tag=TAG).debug(
+                f"VOSK语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text_result.strip()}"
+            )
+            
+            return text_result.strip(), file_path
+            
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"VOSK语音识别失败: {e}")
+            return "", None
+        finally:
+            # 文件清理逻辑
+            if self.delete_audio_file and file_path and os.path.exists(file_path):
+                try:
+                    os.remove(file_path)
+                    logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
+                except Exception as e:
+                    logger.bind(tag=TAG).error(f"文件删除失败: {file_path} | 错误: {e}")
@@ -167,14 +167,13 @@ class ServerMCPClient:

                # 建立SSEClient
                elif "url" in self.config:
+                    headers = dict(self.config.get("headers", {}))
+                    # TODO 兼容旧版本
                    if "API_ACCESS_TOKEN" in self.config:
-                        headers = {
-                            "Authorization": f"Bearer {self.config['API_ACCESS_TOKEN']}"
-                        }
-                    else:
-                        headers = {}
+                        headers["Authorization"] = f"Bearer {self.config['API_ACCESS_TOKEN']}"
+                        self.logger.bind(tag=TAG).warning(f"你正在使用旧过时的配置 API_ACCESS_TOKEN ，请在.mcp_server_settings.json中将API_ACCESS_TOKEN直接设置在headers中，例如 'Authorization': 'Bearer API_ACCESS_TOKEN'")
                    sse_r, sse_w = await stack.enter_async_context(
-                        sse_client(self.config["url"], headers=headers)
+                        sse_client(self.config["url"], headers=headers, timeout=self.config.get("timeout", 5), sse_read_timeout=self.config.get("sse_read_timeout", 60 * 5))
                    )
                    read_stream, write_stream = sse_r, sse_w

@@ -19,6 +19,8 @@ class VoiceprintProvider:
        self.original_url = config.get("url", "")
        self.speakers = config.get("speakers", [])
        self.speaker_map = self._parse_speakers()
+        # 声纹识别相似度阈值，默认0.4
+        self.similarity_threshold = float(config.get("similarity_threshold", 0.4))
        
        # 解析API地址和密钥
        self.api_url = None
@@ -62,7 +64,7 @@ class VoiceprintProvider:
                    # 进行健康检查，验证服务器是否可用
                    if self._check_server_health():
                        self.enabled = True
-                        logger.bind(tag=TAG).info(f"声纹识别已启用: API={self.api_url}, 说话人={len(self.speaker_ids)}个")
+                        logger.bind(tag=TAG).info(f"声纹识别已启用: API={self.api_url}, 说话人={len(self.speaker_ids)}个, 相似度阈值={self.similarity_threshold}")
                    else:
                        self.enabled = False
                        logger.bind(tag=TAG).warning(f"声纹识别服务器不可用，声纹识别已禁用: {self.api_url}")
@@ -169,12 +171,14 @@ class VoiceprintProvider:
                        
                        logger.bind(tag=TAG).info(f"声纹识别耗时: {total_elapsed_time:.3f}s")
                        
-                        # 置信度检查
-                        if score < 0.5:
-                            logger.bind(tag=TAG).warning(f"声纹识别置信度较低: {score:.3f}")
+                        # 相似度阈值检查
+                        if score < self.similarity_threshold:
+                            logger.bind(tag=TAG).warning(f"声纹识别相似度{score:.3f}低于阈值{self.similarity_threshold}")
+                            return "未知说话人"
                        
                        if speaker_id and speaker_id in self.speaker_map:
                            result_name = self.speaker_map[speaker_id]["name"]
+                            logger.bind(tag=TAG).info(f"声纹识别成功: {result_name} (相似度: {score:.3f})")
                            return result_name
                        else:
                            logger.bind(tag=TAG).warning(f"未识别的说话人ID: {speaker_id}")