From 7974ab3f2b825ed4f70a7aafa35733b5efa3b2bf Mon Sep 17 00:00:00 2001
From: Del Wang <wjg12341234@163.com>
Date: Wed, 21 May 2025 19:29:28 +0800
Subject: [PATCH] fix: pause kws on wake up

---
 examples/xiaozhi/xiaozhi/event.py             | 17 ++++++++++-
 .../xiaozhi/services/audio/kws/__init__.py    | 29 ++++++++++++-------
 examples/xiaozhi/xiaozhi/xiaoai.py            | 11 ++-----
 3 files changed, 36 insertions(+), 21 deletions(-)

diff --git a/examples/xiaozhi/xiaozhi/event.py b/examples/xiaozhi/xiaozhi/event.py
index 634a13c..ef637b6 100644
--- a/examples/xiaozhi/xiaozhi/event.py
+++ b/examples/xiaozhi/xiaozhi/event.py
@@ -1,7 +1,14 @@
 import asyncio
 
 from config import APP_CONFIG
-from xiaozhi.ref import get_audio_codec, get_speaker, get_vad, get_xiaoai, get_xiaozhi
+from xiaozhi.ref import (
+    get_audio_codec,
+    get_kws,
+    get_speaker,
+    get_vad,
+    get_xiaoai,
+    get_xiaozhi,
+)
 from xiaozhi.services.protocols.typing import AbortReason, DeviceState, ListeningMode
 
 
@@ -155,5 +162,13 @@ class __EventManager:
         await xiaozhi.protocol.send_stop_listening()
         xiaozhi.set_device_state(DeviceState.IDLE)
 
+    async def wakeup(self, text, source):
+        before_wakeup = APP_CONFIG["wakeup"]["before_wakeup"]
+        get_kws().pause()  # 暂停 KWS 检测
+        wakeup = await before_wakeup(get_speaker(), text, source)
+        get_kws().resume()  # 恢复 KWS 检测
+        if wakeup:
+            self.on_wakeup()
+
 
 EventManager = __EventManager()
diff --git a/examples/xiaozhi/xiaozhi/services/audio/kws/__init__.py b/examples/xiaozhi/xiaozhi/services/audio/kws/__init__.py
index 5003d20..e7b0286 100644
--- a/examples/xiaozhi/xiaozhi/services/audio/kws/__init__.py
+++ b/examples/xiaozhi/xiaozhi/services/audio/kws/__init__.py
@@ -31,6 +31,7 @@ class _KWS:
         )
 
         # 启动 KWS 服务
+        self.paused = False
         self.thread = threading.Thread(target=self._detection_loop, daemon=True)
         self.thread.start()
 
@@ -38,6 +39,12 @@ class _KWS:
         current_dir = os.path.dirname(os.path.abspath(__file__))
         return os.path.join(current_dir, "../../../models", file_name)
 
+    def pause(self):
+        self.paused = True
+
+    def resume(self):
+        self.paused = False
+
     def _detection_loop(self):
         SherpaOnnx.start()
         self.stream.start_stream()
@@ -46,10 +53,15 @@ class _KWS:
             frames = self.stream.read()
 
             # 在说话和监听状态时，暂停 KWS
-            if not frames or get_xiaozhi().device_state in [
-                DeviceState.LISTENING,
-                DeviceState.SPEAKING,
-            ]:
+            if (
+                not frames
+                or self.paused
+                or get_xiaozhi().device_state
+                in [
+                    DeviceState.LISTENING,
+                    DeviceState.SPEAKING,
+                ]
+            ):
                 time.sleep(0.01)
                 continue
 
@@ -60,14 +72,9 @@ class _KWS:
 
     def on_message(self, text: str):
         asyncio.run_coroutine_threadsafe(
-            self._on_message(text), get_xiaoai().async_loop
+            EventManager.wakeup(text, "kws"),
+            get_xiaoai().async_loop,
         )
 
-    async def _on_message(self, text: str):
-        before_wakeup = APP_CONFIG["wakeup"]["before_wakeup"]
-        wakeup = await before_wakeup(get_speaker(), text, "kws")
-        if wakeup:
-            EventManager.on_wakeup()
-
 
 KWS = _KWS()
diff --git a/examples/xiaozhi/xiaozhi/xiaoai.py b/examples/xiaozhi/xiaozhi/xiaoai.py
index cbdeae8..38d0af8 100644
--- a/examples/xiaozhi/xiaozhi/xiaoai.py
+++ b/examples/xiaozhi/xiaozhi/xiaoai.py
@@ -5,7 +5,6 @@ import threading
 import numpy as np
 import open_xiaoai_server
 
-from config import APP_CONFIG
 from xiaozhi.event import EventManager
 from xiaozhi.ref import get_speaker, set_xiaoai
 from xiaozhi.services.audio.stream import GlobalStream
@@ -69,12 +68,6 @@ class XiaoAI:
         event_data = event_json.get("data", {})
         event_type = event_json.get("event")
 
-        async def on_wakeup(text, source):
-            before_wakeup = APP_CONFIG["wakeup"]["before_wakeup"]
-            wakeup = await before_wakeup(get_speaker(), text, source)
-            if wakeup:
-                EventManager.on_wakeup()
-
         if not event_json.get("event"):
             return
 
@@ -87,11 +80,11 @@ class XiaoAI:
             ):
                 text = line.get("payload", {}).get("results")[0].get("text")
                 if not text and not line.get("payload", {}).get("is_vad_begin"):
-                    print(f"🔥 唤醒小爱: {line}")
+                    print("🔥 唤醒小爱")
                     EventManager.on_interrupt()
                 elif text and line.get("payload", {}).get("is_final"):
                     print(f"🔥 收到指令: {text}")
-                    await on_wakeup(text, "xiaoai")
+                    await EventManager.wakeup(text, "xiaoai")
         elif event_type == "playing":
             get_speaker().status = event_data.lower()