update:兼容豆包流式ASR

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

@@ -1,10 +1,15 @@
 import os
+import time
+import copy
 import uuid
 import wave
 import opuslib_next
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
 from typing import Optional, Tuple, List
+from core.utils.util import remove_punctuation_and_length
+from core.handle.reportHandle import enqueue_asr_report
+from core.handle.receiveAudioHandle import startToChat
 
 TAG = __name__
 logger = setup_logging()
@@ -13,6 +18,54 @@ logger = setup_logging()
 class ASRProviderBase(ABC):
     def __init__(self):
         self.audio_format = "opus"
+        self.conn = None
+
+    # 打开音频通道
+    # 这里默认是非流式的处理方式
+    # 流式处理方式请在子类中重写
+    async def open_audio_channels(self, conn):
+        self.conn = conn
+
+    # 接收音频
+    # 这里默认是非流式的处理方式
+    # 流式处理方式请在子类中重写
+    async def receive_audio(self, audio, audio_have_voice):
+        if (
+            self.conn.client_listen_mode == "auto"
+            or self.conn.client_listen_mode == "realtime"
+        ):
+            have_voice = audio_have_voice
+        else:
+            have_voice = self.conn.client_have_voice
+        # 如果本次没有声音，本段也没声音，就把声音丢弃了
+        if have_voice == False and self.conn.client_have_voice == False:
+            self.conn.asr_audio.append(audio)
+            self.conn.asr_audio = self.conn.asr_audio[-10:]
+            return
+
+        # 如果本段有声音，且已经停止了
+        if self.conn.client_voice_stop:
+            self.conn.client_abort = False
+            # 音频太短了，无法识别
+            if len(self.conn.asr_audio) < 15:
+                self.conn.asr_audio.clear()
+                self.conn.reset_vad_states()
+            else:
+                await self.handle_voice_stop()
+
+    # 处理语音停止
+    async def handle_voice_stop(self):
+        raw_text, _ = await self.speech_to_text(
+            self.conn.asr_audio, self.conn.session_id
+        )  # 确保ASR模块返回原始文本
+        self.conn.logger.bind(tag=TAG).info(f"识别文本: {raw_text}")
+        text_len, _ = remove_punctuation_and_length(raw_text)
+        if text_len > 0:
+            # 使用自定义模块进行上报
+            await startToChat(self.conn, raw_text)
+            enqueue_asr_report(self.conn, raw_text, copy.deepcopy(self.conn.asr_audio))
+        self.conn.asr_audio.clear()
+        self.conn.reset_vad_states()
 
     def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
         """PCM数据保存为WAV文件"""