Merge branch 'py_test_typing' into feature/python-typing

main/xiaozhi-server/core/handle/helloHandle.py

@@ -143,7 +143,8 @@ async def wakeupWordsResponse(conn: "ConnectionHandler"):
         # 获取当前音色
         voice = getattr(conn.tts, "voice", "default")
 
-        wav_bytes = opus_datas_to_wav_bytes(tts_result, sample_rate=16000)
+        # 使用链接的sample_rate
+        wav_bytes = opus_datas_to_wav_bytes(tts_result, sample_rate=conn.sample_rate)
         file_path = wakeup_words_config.generate_file_path(voice)
         with open(file_path, "wb") as f:
             f.write(wav_bytes)

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -21,7 +21,6 @@ async def handleAudioMessage(conn: "ConnectionHandler", audio):
     if hasattr(conn, "just_woken_up") and conn.just_woken_up:
         have_voice = False
         # 设置一个短暂延迟后恢复VAD检测
-        conn.asr_audio.clear()
         if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
             conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
         return

main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py

@@ -29,10 +29,9 @@ class ListenTextMessageHandler(TextMessageHandler):
                 f"客户端拾音模式：{conn.client_listen_mode}"
             )
         if msg_json["state"] == "start":
-            conn.client_have_voice = True
-            conn.client_voice_stop = False
+            # 设备从播放模式切回录音模式,清除所有音频状态和缓冲区
+            conn.reset_audio_states()
         elif msg_json["state"] == "stop":
-            conn.client_have_voice = True
             conn.client_voice_stop = True
             if conn.asr.interface_type == InterfaceType.STREAM:
                 # 流式模式下，发送结束请求
@@ -41,14 +40,13 @@ class ListenTextMessageHandler(TextMessageHandler):
                 # 非流式模式：直接触发ASR识别
                 if len(conn.asr_audio) > 0:
                     asr_audio_task = conn.asr_audio.copy()
-                    conn.asr_audio.clear()
-                    conn.reset_vad_states()
+                    conn.reset_audio_states()
 
                     if len(asr_audio_task) > 0:
                         await conn.asr.handle_voice_stop(conn, asr_audio_task)
         elif msg_json["state"] == "detect":
             conn.client_have_voice = False
-            conn.asr_audio.clear()
+            conn.reset_audio_states()
             if "text" in msg_json:
                 conn.last_activity_time = time.time() * 1000
                 original_text = msg_json["text"]  # 保留原始文本