lukehemmin
8f6f8969fd
- api/: FastAPI app, X-API-Key 인증(미설정 시 임시키), 엔진 load-once 풀 (+transcribe lock), POST /v1/transcribe(multipart, 동기), /health, /v1/system, /v1/models. 업로드 임시파일 finally 삭제(프라이버시). - postprocess/: llm.correct(scripts/llm_correct.py 승격; opt-in·allowlist·감사로그·재시도) + rules.normalize(EmbeddingGemma 등 정규화). - results/formats.py: txt/srt/vtt. connectivity/tunnel.py: cloudflared quick tunnel(Colab). - cli serve: uvicorn 단일워커 + --tunnel cloudflare; config llm_* 필드; pyproject api/queue extra 분리(+python-multipart, dev httpx). 검증: 22 단위테스트(API TestClient·formats·postprocess) + 실서버 e2e (/health·auth 401·실제 전사(JFK)·SRT·임시파일 삭제). KO 품질은 turbo/large-v3 필요(tiny는 한국어 degenerate). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
87 lines
2.5 KiB
Python
87 lines
2.5 KiB
Python
"""API — FastAPI TestClient. 엔진은 monkeypatch(가짜)로 모델 로드 회피."""
|
|
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
import luke_scribe.api.routes.transcribe as route
|
|
from luke_scribe.api.app import create_app
|
|
from luke_scribe.config import settings
|
|
|
|
|
|
class _FakeSeg:
|
|
def __init__(self, start: float, end: float, text: str) -> None:
|
|
self.start = start
|
|
self.end = end
|
|
self.text = text
|
|
|
|
|
|
class _FakeEngine:
|
|
def transcribe(self, _audio, **_kw):
|
|
return [_FakeSeg(0.0, 1.0, "안녕 vLLM"), _FakeSeg(1.0, 2.0, "두번째")], SimpleNamespace(
|
|
language="ko"
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def client(monkeypatch):
|
|
monkeypatch.setattr(route, "get_engine", lambda *a, **k: _FakeEngine())
|
|
monkeypatch.setattr(
|
|
route, "probe_media", lambda p: SimpleNamespace(path=p, duration_s=2.0, size_bytes=1234)
|
|
)
|
|
monkeypatch.setattr(settings, "api_keys", ["testkey"])
|
|
return TestClient(create_app())
|
|
|
|
|
|
def _files():
|
|
return {"file": ("a.wav", b"RIFF0000WAVE", "audio/wav")}
|
|
|
|
|
|
def test_health(client):
|
|
assert client.get("/health").json() == {"status": "ok"}
|
|
|
|
|
|
def test_requires_key(client):
|
|
assert client.post("/v1/transcribe", files=_files()).status_code == 401
|
|
|
|
|
|
def test_transcribe_ok(client):
|
|
r = client.post(
|
|
"/v1/transcribe", files=_files(), headers={"X-API-Key": "testkey"}, data={"language": "ko"}
|
|
)
|
|
assert r.status_code == 200
|
|
body = r.json()
|
|
assert body["segments"][0]["text"] == "안녕 vLLM"
|
|
assert body["model_used"]
|
|
assert body["corrected"] is False
|
|
|
|
|
|
def test_413(client, monkeypatch):
|
|
monkeypatch.setattr(
|
|
route, "probe_media", lambda p: SimpleNamespace(path=p, duration_s=999999, size_bytes=1)
|
|
)
|
|
r = client.post("/v1/transcribe", files=_files(), headers={"X-API-Key": "testkey"})
|
|
assert r.status_code == 413
|
|
|
|
|
|
def test_srt_format(client):
|
|
r = client.post(
|
|
"/v1/transcribe",
|
|
files=_files(),
|
|
headers={"X-API-Key": "testkey"},
|
|
data={"response_format": "srt"},
|
|
)
|
|
assert r.status_code == 200
|
|
assert "00:00:00,000 --> 00:00:01,000" in r.text
|
|
|
|
|
|
def test_correct_path(client, monkeypatch):
|
|
monkeypatch.setattr(route.llm_correct, "correct", lambda text, **k: text + " [보정]")
|
|
r = client.post(
|
|
"/v1/transcribe", files=_files(), headers={"X-API-Key": "testkey"}, data={"correct": "true"}
|
|
)
|
|
assert r.status_code == 200
|
|
assert r.json()["corrected"] is True
|