From d13fb73c67ac597a641d561bd645dc4e593bc7fd Mon Sep 17 00:00:00 2001
From: 3030332422 <3030332422@qq.com>
Date: Wed, 9 Jul 2025 14:23:47 +0800
Subject: [PATCH] =?UTF-8?q?update:=E4=BC=98=E5=8C=96?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/config.yaml               | 19 ++++++++++---------
 .../core/handle/sendAudioHandle.py            | 16 +++++++++++++++-
 .../xiaozhi-server/core/providers/asr/base.py |  2 +-
 main/xiaozhi-server/core/utils/dialogue.py    |  2 +-
 .../core/utils/modules_initialize.py          |  2 +-
 .../core/utils/voiceprint_provider.py         |  3 +--
 6 files changed, 29 insertions(+), 15 deletions(-)

diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml
index 5b746866..36156438 100644
--- a/main/xiaozhi-server/config.yaml
+++ b/main/xiaozhi-server/config.yaml
@@ -137,15 +137,16 @@ plugins:
       - ".wav"
       - ".p3"
     refresh_time: 300 # 刷新音乐列表的时间间隔，单位为秒
-  # 声纹识别配置
-  voiceprint:
-    # 声纹接口地址
-    url: 
-    # 说话人配置：speaker_id,名称,描述
-    speakers:
-      - "test1,张三,张三是一个程序员"
-      - "test2,李四,李四是一个产品经理"
-      - "test3,王五,王五是一个设计师"
+
+# 声纹识别配置
+voiceprint:
+  # 声纹接口地址
+  url: 
+  # 说话人配置：speaker_id,名称,描述
+  speakers:
+    - "test1,张三,张三是一个程序员"
+    - "test2,李四,李四是一个产品经理"
+    - "test3,王五,王五是一个设计师"
 
 # #####################################################################################
 # ################################以下是角色模型配置######################################
diff --git a/main/xiaozhi-server/core/handle/sendAudioHandle.py b/main/xiaozhi-server/core/handle/sendAudioHandle.py
index 7bb40d78..486e6d90 100644
--- a/main/xiaozhi-server/core/handle/sendAudioHandle.py
+++ b/main/xiaozhi-server/core/handle/sendAudioHandle.py
@@ -136,7 +136,21 @@ async def send_stt_message(conn, text):
         return
 
     """发送 STT 状态消息"""
-    stt_text = get_string_no_punctuation_or_emoji(text)
+    
+    # 解析JSON格式，提取实际的用户说话内容
+    display_text = text
+    try:
+        # 尝试解析JSON格式
+        if text.strip().startswith('{') and text.strip().endswith('}'):
+            parsed_data = json.loads(text)
+            if isinstance(parsed_data, dict) and "content" in parsed_data:
+                # 如果是包含说话人信息的JSON格式，只显示content部分
+                display_text = parsed_data["content"]
+    except (json.JSONDecodeError, TypeError):
+        # 如果不是JSON格式，直接使用原始文本
+        display_text = text
+    
+    stt_text = get_string_no_punctuation_or_emoji(display_text)
     await conn.websocket.send(
         json.dumps({"type": "stt", "text": stt_text, "session_id": conn.session_id})
     )
diff --git a/main/xiaozhi-server/core/providers/asr/base.py b/main/xiaozhi-server/core/providers/asr/base.py
index 142e703f..ef9fa01e 100644
--- a/main/xiaozhi-server/core/providers/asr/base.py
+++ b/main/xiaozhi-server/core/providers/asr/base.py
@@ -192,7 +192,7 @@ class ASRProviderBase(ABC):
 
     def _build_enhanced_text(self, text: str, speaker_name: Optional[str]) -> str:
         """构建包含说话人信息的文本"""
-        if speaker_name:
+        if speaker_name and speaker_name.strip():
             return json.dumps({
                 "speaker": speaker_name,
                 "content": text
diff --git a/main/xiaozhi-server/core/utils/dialogue.py b/main/xiaozhi-server/core/utils/dialogue.py
index 69fb250e..fc45a108 100644
--- a/main/xiaozhi-server/core/utils/dialogue.py
+++ b/main/xiaozhi-server/core/utils/dialogue.py
@@ -84,7 +84,7 @@ class Dialogue:
             # 添加说话人个性化描述
             try:
                 config = load_config()
-                voiceprint_config = config.get("plugins", {}).get("voiceprint", {})
+                voiceprint_config = config.get("voiceprint", {})
                 speakers = voiceprint_config.get("speakers", [])
                 
                 if speakers:
diff --git a/main/xiaozhi-server/core/utils/modules_initialize.py b/main/xiaozhi-server/core/utils/modules_initialize.py
index 43f3e470..a8db1630 100644
--- a/main/xiaozhi-server/core/utils/modules_initialize.py
+++ b/main/xiaozhi-server/core/utils/modules_initialize.py
@@ -127,7 +127,7 @@ def initialize_asr(config):
     )
     
     # 初始化声纹识别功能
-    voiceprint_config = config.get("plugins", {}).get("voiceprint")
+    voiceprint_config = config.get("voiceprint")
     if voiceprint_config and voiceprint_config.get("url") and voiceprint_config.get("speakers"):
         new_asr.init_voiceprint(voiceprint_config)
         logger.bind(tag=TAG).info("ASR模块声纹识别功能已启用")
diff --git a/main/xiaozhi-server/core/utils/voiceprint_provider.py b/main/xiaozhi-server/core/utils/voiceprint_provider.py
index b241fb51..deec20c8 100644
--- a/main/xiaozhi-server/core/utils/voiceprint_provider.py
+++ b/main/xiaozhi-server/core/utils/voiceprint_provider.py
@@ -118,8 +118,7 @@ class VoiceprintProvider:
                             result_name = self.speaker_map[speaker_id]["name"]
                             return result_name
                         else:
-                            logger.bind(tag=TAG).warning(f"未识别的说话人ID: {speaker_id}")
-                            return "未知说话人"
+                            return None
                     else:
                         logger.bind(tag=TAG).error(f"声纹识别API错误: HTTP {response.status}")
                         return None