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

View File

@@ -0,0 +1,49 @@
"""分片上传会话 ORM支撑断点续传。对齐 server 的 UploadSession 形态SQLite 版)。"""
from __future__ import annotations
import json
from datetime import datetime, timezone
from typing import Any
from sqlalchemy import DateTime, ForeignKey, Integer, String, Text, TypeDecorator
from sqlalchemy.orm import Mapped, mapped_column
from ..database import Base
def _now() -> datetime:
return datetime.now(timezone.utc)
class _IntList(TypeDecorator):
"""把 list[int] 存成 JSON 字符串。SQLite 没有 ARRAY 类型。"""
impl = Text
cache_ok = True
def process_bind_param(self, value: Any, dialect) -> str | None:
return json.dumps(value) if value is not None else None
def process_result_value(self, value: Any, dialect) -> list[int]:
return json.loads(value) if value else []
class UploadSession(Base):
__tablename__ = "upload_session"
upload_id: Mapped[str] = mapped_column(String(64), primary_key=True)
filename: Mapped[str] = mapped_column(String(512), nullable=False)
size_bytes: Mapped[int] = mapped_column(Integer, nullable=False)
chunk_size: Mapped[int] = mapped_column(Integer, nullable=False)
total_chunks: Mapped[int] = mapped_column(Integer, nullable=False)
uploaded_chunks: Mapped[list[int]] = mapped_column(_IntList, default=list)
# pending → completedcomplete 成功)| abandonedreaper 清理)
status: Mapped[str] = mapped_column(String(32), nullable=False, default="pending")
# 拼接完成后的视频相对 upload_dir 路径
final_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
# complete 后关联的 Task.id直接引用避免反向查找 source_path
task_id: Mapped[int | None] = mapped_column(ForeignKey("task.id"), nullable=True)
created_at: Mapped[datetime] = mapped_column(DateTime, default=_now)
updated_at: Mapped[datetime] = mapped_column(DateTime, default=_now, onupdate=_now)