31 lines
1.2 KiB
Plaintext
31 lines
1.2 KiB
Plaintext
1、ASR
|
||
D:\dsWork\QingLong\XiaoZhi\xiaozhi-esp32-server\main\xiaozhi-server\core\handle\receiveAudioHandle.py
|
||
|
||
在第12行，大约这个位置下断点，可以跟踪到流程
|
||
async def handleAudioMessage(conn, audio):
|
||
if not conn.asr_server_receive:
|
||
|
||
某些场景下，在38行下断点可以拦截到内容
|
||
if conn.client_voice_stop:
|
||
conn.client_abort = False
|
||
conn.asr_server_receive = False
|
||
# 音频太短了，无法识别
|
||
if len(conn.asr_audio) < 15:
|
||
conn.asr_server_receive = True
|
||
else:
|
||
text, file_path = await conn.asr.speech_to_text(
|
||
conn.asr_audio, conn.session_id
|
||
)
|
||
|
||
跟踪进入
|
||
D:\dsWork\QingLong\XiaoZhi\xiaozhi-esp32-server\main\xiaozhi-server\core\providers\asr\fun_local.py
|
||
76行
|
||
async def speech_to_text(self, opus_data: List[bytes], session_id: str) -> Tuple[Optional[str], Optional[str]]:
|
||
"""语音转文本主处理逻辑"""
|
||
file_path = None
|
||
try:
|
||
|
||
准备在第97行嵌入代码：
|
||
#【黄海注释】准备在这里进行嵌入代码，把文字+声音的关系记录下来，让用户选择是哪个人进行声纹匹配
|
||
|
||
return text, file_path |