Initial commit: audio2text 双语字幕生成服务

- 音频/视频转双语(英/中)SRT 字幕,Docker 容器化,CPU 开发/GPU 生产同一份代码
- faster-whisper ASR(词级时间戳) + 断句时间戳重算 + NLLB 翻译(模型不共驻)
- 分片上传(断点续传) + SQLite 持久化 + 主页/历史/日志页面
- 历史页文件名搜索;缓存定时清理(默认保留7天,可配置)
- 双 Dockerfile(cpu/gpu) + setup/start/stop 脚本
This commit is contained in:
2026-07-06 06:54:19 +00:00
commit 00e2a95fb7
44 changed files with 4110 additions and 0 deletions

68
app/database.py Normal file
View File

@@ -0,0 +1,68 @@
"""SQLite 引擎、Session、Base、get_db 依赖。
自包含:无需外部 MySQL容器内单文件 SQLite 即可。对齐 server/database.py 的接口形态,
但用 SQLite本项目独立运行、无并发写入压力
"""
from __future__ import annotations
from pathlib import Path
from typing import Generator
from sqlalchemy import create_engine
from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
from .config import get_settings
_engine = None
_SessionLocal = None
def _db_path() -> Path:
"""SQLite 文件落在 work_dir 下,跟数据一起走 volume。"""
s = get_settings()
p = s.work_dir() / "audio2text.db"
p.parent.mkdir(parents=True, exist_ok=True)
return p
def get_engine():
global _engine, _SessionLocal
if _engine is None:
url = f"sqlite:///{_db_path()}"
_engine = create_engine(
url,
# 后台 reaper / 缓存清理线程与请求线程并发写同一库busy_timeout 让等待方
# 在拿锁时阻塞 5s 而非立即报 database is locked。
connect_args={"check_same_thread": False, "timeout": 30},
future=True,
)
_SessionLocal = sessionmaker(bind=_engine, autoflush=False, expire_on_commit=False)
return _engine
def get_session_local():
get_engine()
return _SessionLocal
class Base(DeclarativeBase):
pass
def init_db_schema() -> None:
"""建表(幂等)。"""
from .models.task import Task # noqa: F401
from .models.upload_session import UploadSession # noqa: F401
get_engine()
Base.metadata.create_all(get_engine())
def get_db() -> Generator[Session, None, None]:
"""FastAPI 依赖:每请求一个 Session结束自动关闭。"""
db = get_session_local()()
try:
yield db
finally:
db.close()