update:修复iot的bug (#407)

* fix: 修复manual模式无法识别 (#404)

* feat(docs): 新增Issues模板

* fix: 补全core依赖

* fix: 修复manual模式无法识别

* 去除重复依赖.txt

已经有torch和torchaudio

---------

Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com>

* 修复iot功能中表达式问题 (#400)

* Custom paths asr tts (#388)

* #164 自定义asr、tts缓存目录,项目启动自动创建目录

* #164 自定义asr、tts缓存目录,项目启动自动创建目录

* fix:修复语音无法找到新配置项output_file的bug

* fix：电脑不支持iot音量控制bug

---------

Co-authored-by: Junsen <66542771+Huang-junsen@users.noreply.github.com>
Co-authored-by: tang <tangyiyong@gmail.com>
Co-authored-by: shudongW <178200623@qq.com>
Co-authored-by: hrz <1710360675@qq.com>

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

@@ -197,12 +197,12 @@ def register_device_type(descriptor):
 
     # 为每个属性创建查询函数
     for prop_name, prop_info in descriptor["properties"].items():
-        func_name = f"get_{device_name.lower()}_{prop_name.lower()}"
+        func_name = f"get_{{device_name.lower()}}_{{prop_name.lower()}}"
         func_desc = {
             "type": "function",
             "function": {
                 "name": func_name,
-                "description": f"查询{descriptor['description']}的{prop_info['description']}",
+                "description": f"查询{{descriptor['description']}}的{{prop_info['description']}}",
                 "parameters": {
                     "type": "object",
                     "properties": {
@@ -212,7 +212,7 @@ def register_device_type(descriptor):
                         },
                         "response_failure": {
                             "type": "string",
-                            "description": "查询失败时的友好回复，例如：'无法获取{device_name}的{prop_info['description']}'"
+                            "description": f"查询失败时的友好回复，例如：'无法获取{{device_name}}的{{prop_info['description']}}'"
                         }
                     },
                     "required": ["response_success", "response_failure"]
@@ -256,7 +256,7 @@ def register_device_type(descriptor):
             "type": "function",
             "function": {
                 "name": func_name,
-                "description": f"{descriptor['description']} - {method_info['description']}",
+                "description": f"{{descriptor['description']}} - {{method_info['description']}}",
                 "parameters": {
                     "type": "object",
                     "properties": parameters,

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

@@ -2,7 +2,7 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
-from core.handle.receiveAudioHandle import startToChat
+from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
 from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
@@ -24,13 +24,15 @@ async def handleTextMessage(conn, message):
         elif msg_json["type"] == "listen":
             if "mode" in msg_json:
                 conn.client_listen_mode = msg_json["mode"]
-                logger.bind(tag=TAG).debug(f"客户端拾音模式：{conn.client_listen_mode}")
+                logger.bind(tag=TAG).debug(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
             elif msg_json["state"] == "stop":
                 conn.client_have_voice = True
                 conn.client_voice_stop = True
+                if len(conn.asr_audio) > 0:
+                    await handleAudioMessage(conn, b'')
             elif msg_json["state"] == "detect":
                 conn.asr_server_receive = False
                 conn.client_have_voice = False

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

@@ -13,7 +13,7 @@ logger = setup_logging()
 class TTSProviderBase(ABC):
     def __init__(self, config, delete_audio_file):
         self.delete_audio_file = delete_audio_file
-        self.output_file = config.get("output_file")
+        self.output_file = config.get("output_dir")
 
     @abstractmethod
     def generate_filename(self):

main/xiaozhi-server/core/providers/tts/custom.py

@@ -15,7 +15,7 @@ class TTSProvider(TTSProviderBase):
         self.headers = config.get("headers", {})
         self.params = config.get("params")
         self.format = config.get("format", "wav")
-        self.output_file = config.get("output_file", "tmp/")
+        self.output_file = config.get("output_dir", "tmp/")
 
     def generate_filename(self):
         return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}.{self.format}")

main/xiaozhi-server/core/providers/tts/openai.py

@@ -14,7 +14,7 @@ class TTSProvider(TTSProviderBase):
         self.voice = config.get("voice", "alloy")
         self.response_format = "wav"
         self.speed = config.get("speed", 1.0)
-        self.output_file = config.get("output_file", "tmp/")
+        self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 
     def generate_filename(self, extension=".wav"):

main/xiaozhi-server/core/providers/tts/ttson.py

@@ -17,7 +17,7 @@ class TTSProvider(TTSProviderBase):
         self.volume_change_dB = config.get("volume_change_dB", 0)
         self.speed_factor = config.get("speed_factor", 1)
         self.stream = config.get("stream", False)
-        self.output_file = config.get("output_file")
+        self.output_file = config.get("output_dir")
         self.pitch_factor = config.get("pitch_factor", 0)
         self.format = config.get("format", "mp3")
         self.emotion = config.get("emotion", 1)