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

40
app/models/task.py Normal file
View File

@@ -0,0 +1,40 @@
"""Task ORM一个上传完成的视频对应一个转写任务承载状态机。"""
from __future__ import annotations
from datetime import datetime, timezone
from sqlalchemy import DateTime, Float, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from ..database import Base
def _now() -> datetime:
return datetime.now(timezone.utc)
class Task(Base):
__tablename__ = "task"
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
# 原始视频文件名(用户上传时的名字)
filename: Mapped[str] = mapped_column(String(512), nullable=False)
# 视频在 upload_dir 下的相对路径(提取音频前后可能被删)
source_path: Mapped[str] = mapped_column(String(1024), nullable=False)
# 状态机queued → extracting → transcribing → segmenting → translating → done | failed
status: Mapped[str] = mapped_column(String(32), nullable=False, default="queued")
# 0-100 进度
progress: Mapped[float] = mapped_column(Float, nullable=False, default=0.0)
# 失败原因
error: Mapped[str | None] = mapped_column(Text, nullable=True)
# 输出字幕路径(双语合并 / 英文 / 中文)
bilingual_srt_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
en_srt_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
zh_srt_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
created_at: Mapped[datetime] = mapped_column(DateTime, default=_now)
updated_at: Mapped[datetime] = mapped_column(DateTime, default=_now, onupdate=_now)
def __repr__(self) -> str:
return f"<Task id={self.id} {self.filename} status={self.status}>"