73110848f4
- scheduler: ffmpeg 异步线程 + GPU 串行调度 + 模型复用（2N→2 次加载） - pipeline: 阶段拆分（extract/asr/translate），中间数据存 Task 字段 - translate_service: 长度排序批处理，padding 浪费减少 91% - model_manager: ASR/翻译不共驻，BatchedInferencePipeline 批量解码 - 日志分级: INFO=任务流转里程碑，DEBUG=进度详情；默认 INFO - 前端: 日志最新在上+滚动感知+退避轮询；24h 时间；上传中状态显示 - /health: 返回完整 Whisper/NLLB 配置 - upload_service: 单事务 complete + 扩展名白名单 - task_router: 合并 UploadSession 虚拟任务到列表 - Dockerfile: CPU/GPU 独立构建链，deps 缓存稳定 - prefetch_models: 安装时预下载模型权重
83 lines
2.1 KiB
YAML
83 lines
2.1 KiB
YAML
# audio2text — 双语字幕生成服务
|
||
# CPU dev / GPU prod 两套配置，按需切换 service。
|
||
#
|
||
# 开发（CPU，热重载，改代码零重建）：
|
||
# docker compose --profile dev up -d --build
|
||
# CPU 生产：
|
||
# docker compose --profile cpu up -d --build
|
||
# GPU 生产（本机有 nvidia runtime 时）：
|
||
# docker compose --profile gpu up -d --build
|
||
#
|
||
# 模型缓存（/models）跨容器复用，首次启动下载、之后秒起。
|
||
# pip wheel 缓存由 BuildKit --mount=type=cache 管理，跨构建复用。
|
||
|
||
services:
|
||
# ---------------- 开发：CPU + 源码挂载 + uvicorn reload ----------------
|
||
# 改 app/ 下代码无需重建镜像，保存即热重载。
|
||
audio2text-cpu-dev:
|
||
build:
|
||
context: .
|
||
args:
|
||
VARIANT: cpu
|
||
target: dev
|
||
image: audio2text:cpu-dev
|
||
container_name: audio2text-dev
|
||
ports:
|
||
- "8000:8000"
|
||
volumes:
|
||
- ./app:/app/app
|
||
- ./data:/data
|
||
- ./models:/models
|
||
- ./config.yaml:/app/config.yaml:ro
|
||
environment:
|
||
CONFIG_PATH: /app/config.yaml
|
||
restart: unless-stopped
|
||
profiles: ["dev"]
|
||
|
||
# ---------------- CPU 生产 ----------------
|
||
audio2text-cpu:
|
||
build:
|
||
context: .
|
||
args:
|
||
VARIANT: cpu
|
||
target: final
|
||
image: audio2text:cpu
|
||
container_name: audio2text
|
||
ports:
|
||
- "8000:8000"
|
||
volumes:
|
||
- ./data:/data
|
||
- ./models:/models
|
||
- ./config.yaml:/app/config.yaml:ro
|
||
environment:
|
||
CONFIG_PATH: /app/config.yaml
|
||
restart: unless-stopped
|
||
profiles: ["cpu", ""]
|
||
|
||
# ---------------- GPU 生产 ----------------
|
||
audio2text-gpu:
|
||
build:
|
||
context: .
|
||
args:
|
||
VARIANT: gpu
|
||
target: final
|
||
image: audio2text:gpu
|
||
container_name: audio2text-gpu
|
||
ports:
|
||
- "8001:8000"
|
||
volumes:
|
||
- ./data:/data
|
||
- ./models:/models
|
||
- ./config.gpu.yaml:/app/config.yaml:ro
|
||
environment:
|
||
CONFIG_PATH: /app/config.yaml
|
||
deploy:
|
||
resources:
|
||
reservations:
|
||
devices:
|
||
- driver: nvidia
|
||
count: all
|
||
capabilities: [gpu]
|
||
restart: unless-stopped
|
||
profiles: ["gpu"]
|