Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 07:03:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 优化上报命名含义，增加不同上报开关

Browse Source
This commit is contained in:
goodyhao
2025-05-12 19:14:04 +08:00
parent 6e210faacf
commit 0b11953f6f
4 changed files with 63 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/connection.py
+21 -19
View File
@@ -33,7 +33,7 @@ from core.mcp.manager import MCPManager
from config.config_loader import get_private_config_from_api
from config.manage_api_client import DeviceNotFoundException, DeviceBindException
from core.utils.output_counter import add_device_output
from core.handle.ttsReportHandle import enqueue_tts_report, report_tts
from core.handle.reportHandle import enqueue_tts_report, report
TAG = __name__
@@ -89,8 +89,11 @@ class ConnectionHandler:
self.executor = ThreadPoolExecutor(max_workers=10)
# 上报线程
self.tts_report_queue = queue.Queue()
self.tts_report_thread = None
self.report_queue = queue.Queue()
self.report_thread = None
# TODO(haotian): 2025/5/12 可以通过修改此处，调节asr的上报和tts的上报
self.report_asr_enable = self.read_config_from_api
self.report_tts_enable = self.read_config_from_api
# 依赖的组件
self.vad = None
@@ -317,11 +320,11 @@ class ConnectionHandler:
return
if self.chat_history_conf == 0:
return
if self.tts_report_thread is None or not self.tts_report_thread.is_alive():
self.tts_report_thread = threading.Thread(
target=self._tts_report_worker, daemon=True
if self.report_thread is None or not self.report_thread.is_alive():
self.report_thread = threading.Thread(
target=self._report_worker, daemon=True
)
self.tts_report_thread.start()
self.report_thread.start()
self.logger.bind(tag=TAG).info("TTS上报线程已启动")
def _initialize_private_config(self):
@@ -872,8 +875,8 @@ class ConnectionHandler:
audio_datas, _ = self.tts.audio_to_pcm_data(tts_file)
else:
audio_datas, _ = self.tts.audio_to_opus_data(tts_file)
# 在这里上报TTS数据（使用文件路径）
enqueue_tts_report(self, 2, text, audio_datas)
# 在这里上报TTS数据
enqueue_tts_report(self, text, audio_datas)
else:
self.logger.bind(tag=TAG).error(
f"TTS出错：文件不存在{tts_file}"
@@ -929,13 +932,12 @@ class ConnectionHandler:
f"audio_play_priority priority_thread: {text} {e}"
)
def _tts_report_worker(self):
"""TTS上报工作线程"""
def _report_worker(self):
"""聊天记录上报工作线程"""
while not self.stop_event.is_set():
try:
# 从队列获取数据，设置超时以便定期检查停止事件
item = self.tts_report_queue.get(timeout=1)
item = self.report_queue.get(timeout=1)
if item is None: # 检测毒丸对象
break
@@ -943,18 +945,18 @@ class ConnectionHandler:
try:
# 执行上报（传入二进制数据）
report_tts(self, type, text, audio_data)
report(self, type, text, audio_data)
except Exception as e:
self.logger.bind(tag=TAG).error(f"TTS上报线程异常: {e}")
self.logger.bind(tag=TAG).error(f"聊天记录上报线程异常: {e}")
finally:
# 标记任务完成
self.tts_report_queue.task_done()
self.report_queue.task_done()
except queue.Empty:
continue
except Exception as e:
self.logger.bind(tag=TAG).error(f"TTS上报工作线程异常: {e}")
self.logger.bind(tag=TAG).error(f"聊天记录上报工作线程异常: {e}")
self.logger.bind(tag=TAG).info("TTS上报线程已退出")
self.logger.bind(tag=TAG).info("聊天记录上报线程已退出")
def speak_and_play(self, text, text_index=0):
if text is None or len(text) <= 0:
@@ -1002,7 +1004,7 @@ class ConnectionHandler:
self.executor = None
# 添加毒丸对象到上报队列确保线程退出
self.tts_report_queue.put(None)
self.report_queue.put(None)
# 清空任务队列
self.clear_queues()
main/xiaozhi-server/core/handle/receiveAudioHandle.py
+2 -2
View File
@@ -4,7 +4,7 @@ from core.utils.util import remove_punctuation_and_length
from core.handle.sendAudioHandle import send_stt_message
from core.handle.intentHandler import handle_user_intent
from core.utils.output_counter import check_device_output_limit
from core.handle.ttsReportHandle import enqueue_tts_report
from core.handle.reportHandle import enqueue_asr_report
from core.utils.util import audio_to_data
TAG = __name__
@@ -44,7 +44,7 @@ async def handleAudioMessage(conn, audio):
text_len, _ = remove_punctuation_and_length(text)
if text_len > 0:
# 使用自定义模块进行上报
enqueue_tts_report(conn, 1, text, copy.deepcopy(conn.asr_audio))
enqueue_asr_report(conn, text, copy.deepcopy(conn.asr_audio))
await startToChat(conn, text)
else:
main/xiaozhi-server/core/handle/ttsReportHandle.py → main/xiaozhi-server/core/handle/reportHandle.py
+37 -9
View File
@@ -11,13 +11,13 @@ TTS上报功能已集成到ConnectionHandler类中。
import opuslib_next
from config.manage_api_client import report
from config.manage_api_client import report as manage_report
TAG = __name__
def report_tts(conn, type, text, opus_data):
"""执行TTS上报操作
def report(conn, type, text, opus_data):
"""执行聊天记录上报操作
Args:
conn: 连接对象
@@ -31,7 +31,7 @@ def report_tts(conn, type, text, opus_data):
else:
audio_data = None
# 执行上报
report(
manage_report(
mac_address=conn.device_id,
session_id=conn.session_id,
chat_type=type,
@@ -39,7 +39,7 @@ def report_tts(conn, type, text, opus_data):
audio=audio_data,
)
except Exception as e:
conn.logger.bind(tag=TAG).error(f"TTS上报失败: {e}")
conn.logger.bind(tag=TAG).error(f"聊天记录上报失败: {e}")
def opus_to_wav(conn, opus_data):
@@ -89,8 +89,8 @@ def opus_to_wav(conn, opus_data):
return bytes(wav_header) + pcm_data_bytes
def enqueue_tts_report(conn, type, text, opus_data):
if not conn.read_config_from_api or conn.need_bind:
def enqueue_tts_report(conn, text, opus_data):
if not conn.read_config_from_api or conn.need_bind or not conn.report_tts_enable:
return
if conn.chat_history_conf == 0:
return
@@ -104,14 +104,42 @@ def enqueue_tts_report(conn, type, text, opus_data):
try:
# 使用连接对象的队列，传入文本和二进制数据而非文件路径
if conn.chat_history_conf == 2:
conn.tts_report_queue.put((type, text, opus_data))
conn.report_queue.put((2, text, opus_data))
conn.logger.bind(tag=TAG).debug(
f"TTS数据已加入上报队列: {conn.device_id}, 音频大小: {len(opus_data)} "
)
else:
conn.tts_report_queue.put((type, text, None))
conn.report_queue.put((2, text, None))
conn.logger.bind(tag=TAG).debug(
f"TTS数据已加入上报队列: {conn.device_id}, 不上报音频"
)
except Exception as e:
conn.logger.bind(tag=TAG).error(f"加入TTS上报队列失败: {text}, {e}")
def enqueue_asr_report(conn, text, opus_data):
if not conn.read_config_from_api or conn.need_bind or not conn.report_asr_enable:
return
if conn.chat_history_conf == 0:
return
"""将ASR数据加入上报队列
Args:
conn: 连接对象
text: 合成文本
opus_data: opus音频数据
"""
try:
# 使用连接对象的队列，传入文本和二进制数据而非文件路径
if conn.chat_history_conf == 2:
conn.report_queue.put((1, text, opus_data))
conn.logger.bind(tag=TAG).debug(
f"ASR数据已加入上报队列: {conn.device_id}, 音频大小: {len(opus_data)} "
)
else:
conn.report_queue.put((1, text, None))
conn.logger.bind(tag=TAG).debug(
f"ASR数据已加入上报队列: {conn.device_id}, 不上报音频"
)
except Exception as e:
conn.logger.bind(tag=TAG).error(f"加入ASR上报队列失败: {text}, {e}")
main/xiaozhi-server/core/handle/textHandle.py
+3 -3
View File
@@ -5,7 +5,7 @@ from core.utils.util import remove_punctuation_and_length
from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
from core.handle.sendAudioHandle import send_stt_message, send_tts_message
from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
from core.handle.ttsReportHandle import enqueue_tts_report
from core.handle.reportHandle import enqueue_asr_report
import asyncio
TAG = __name__
@@ -56,11 +56,11 @@ async def handleTextMessage(conn, message):
await send_tts_message(conn, "stop", None)
elif is_wakeup_words:
# 上报纯文字数据（复用ASR上报功能，但不提供音频数据）
enqueue_tts_report(conn, 1, "嘿，你好呀", [])
enqueue_asr_report(conn, "嘿，你好呀", [])
await startToChat(conn, "嘿，你好呀")
else:
# 上报纯文字数据（复用ASR上报功能，但不提供音频数据）
enqueue_tts_report(conn, 1, text, [])
enqueue_asr_report(conn, text, [])
# 否则需要LLM对文字内容进行答复
await startToChat(conn, text)
elif msg_json["type"] == "iot":