zcbot/scripts/diag_asr.py

68 lines
2.2 KiB
Python

"""讯飞语音听写(IAT)诊断:验证 XFYUN_* 凭据 + wss 协议链路是否通。
用法(.env 在仓库根):
.venv/Scripts/python.exe scripts/diag_asr.py # 2s 静音冒烟(验鉴权/协议,预期空文本)
.venv/Scripts/python.exe scripts/diag_asr.py <pcm文件> # 真实音频(16k/16bit/mono 裸 PCM)
ASCII 输出(Windows 控制台 GBK,不打 emoji);secret 不打印。
常见错误码:10105/10313=appid 错;11200=服务未开通或量用完;11201=当日超限。
"""
import asyncio
import os
import sys
_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
if _ROOT not in sys.path:
sys.path.insert(0, _ROOT)
def _load_env(path: str) -> None:
try:
from dotenv import load_dotenv
load_dotenv(path)
return
except Exception:
pass
try:
with open(path, encoding="utf-8") as f:
for line in f:
line = line.strip()
if not line or line.startswith("#") or "=" not in line:
continue
k, v = line.split("=", 1)
os.environ.setdefault(k.strip(), v.strip().strip('"').strip("'"))
except FileNotFoundError:
pass
_load_env(os.path.join(_ROOT, ".env"))
from core.asr_xfyun import SAMPLE_RATE, XfyunASRError, transcribe # noqa: E402
def main() -> int:
appid = os.getenv("XFYUN_APPID", "")
print(f"[env] XFYUN_APPID={appid or '(missing)'} "
f"API_KEY={'set' if os.getenv('XFYUN_API_KEY') else '(missing)'} "
f"API_SECRET={'set' if os.getenv('XFYUN_API_SECRET') else '(missing)'}")
if len(sys.argv) > 1:
pcm = open(sys.argv[1], "rb").read()
print(f"[audio] file={sys.argv[1]} bytes={len(pcm)} "
f"({len(pcm) / (SAMPLE_RATE * 2):.1f}s @16k/16bit/mono)")
else:
pcm = b"\x00" * (SAMPLE_RATE * 2 * 2) # 2s 静音:只验鉴权+协议,预期识别为空
print("[audio] builtin 2s silence (auth/protocol smoke, empty text expected)")
try:
text = asyncio.run(transcribe(pcm))
except XfyunASRError as e:
print(f"[FAIL] code={e.code} {e}")
return 1
print(f"[OK] text={text!r}")
return 0
if __name__ == "__main__":
sys.exit(main())