
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具,协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题,请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可:
请先完整阅读并严格遵守以下文档中的全部规则与要求:
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前,不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式,不推荐豆包 AI;Cursor 等编辑器可在对话 @ 该链接,或加入 User Rules。 若 AI 无法访问外链,可 打开说明文档 复制全文粘贴。文档会随站点更新,复制内容可能过期,建议定期检查。
Home Assistant插件,使用https://github.com/rhasspy/wyoming-faster-whisper%E9%80%9A%E8%BF%87%60wyoming%E5%8D%8F%E8%AE%AE%60%E5%9C%A8**NVIDIA Jetson**设备上实现语音转文本系统。感谢https://github.com/ms1design%E8%B4%A1%E7%8C%AE%E8%BF%99%E4%BA%9BHome Assistant与Wyoming容器!
home-assistant-core容器以及不同主机上托管的Home Assistant兼容良好faster-whisper容器,在Jetson设备上实现GPU加速需要Home Assistant
2023.9或更高版本。
docker-compose示例如果您想使用docker compose在启用cuda的Jetson设备上运行https://github.com/dusty-nv/jetson-containers/tree/master/packages/smart-home/homeassistant-core/ 语音助手管道,可在此处找到完整示例https://github.com/dusty-nv/jetson-containers/tree/master/packages/smart-home/wyoming/docker-compose.yaml%E3%80%82
yamlname: home-assistant-jetson version: "3.9" services: homeassistant: image: dustynv/homeassistant-core:latest-r36.2.0 restart: unless-stopped init: false privileged: true network_mode: host container_name: homeassistant hostname: homeassistant ports: - "8123:8123" volumes: - ha-config:/config - /etc/localtime:/etc/localtime:ro - /etc/timezone:/etc/timezone:ro whisper: image: dustynv/wyoming-whisper:latest-r36.2.0 restart: unless-stopped runtime: nvidia network_mode: host container_name: faster-whisper hostname: faster-whisper init: false ports: - "10300:10300/tcp" volumes: - ha-whisper-models:/share/whisper - ha-whisper-data:/data - /etc/localtime:/etc/localtime:ro - /etc/timezone:/etc/timezone:ro volumes: ha-config: ha-whisper-models: ha-whisper-data:
| 变量 | 类型 | 默认值 | 描述 |
|---|---|---|---|
WHISPER_PORT | str | 10300 | 主机上使用的端口号 |
WHISPER_MODEL | str | tiny-int8 | 要使用的faster-whisper模型名称,来自https://github.com/home-assistant/addons/blob/master/whisper/config.yaml#L22 |
WHISPER_BEAM_SIZE | int | 1 | 波束搜索大小 |
WHISPER_LANGUAGE | str | en | 转录的默认语言,来自https://github.com/home-assistant/addons/blob/master/whisper/config.yaml#L25 |
WHISPER_DEBUG | bool | true | 记录DEBUG级别的日志 |
阅读官方文档了解如何配置wyoming-whisper。
有问题?您有以下几种方式获取解答:
/r/homeassistantjetson-containers中的错误,请在https://github.com/dusty-nv/jetson-containers/issues[!NOTE] 此项目由Jetson AI Lab研究小组创建。
wyoming-whisper:latest | |
|---|---|
| 别名 | wyoming-whisper |
| 要求 | L4T ['>=34.1.0'] |
| 依赖项 | https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/build-essential https://github.com/dusty-nv/jetson-containers/tree/master/packages/smart-home/homeassistant-base https://github.com/dusty-nv/jetson-containers/tree/master/packages/cuda/cuda https://github.com/dusty-nv/jetson-containers/tree/master/packages/cuda/cudnn https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/python https://github.com/dusty-nv/jetson-containers/tree/master/packages/build/cmake/cmake_pip https://github.com/dusty-nv/jetson-containers/tree/master/packages/ctranslate2 https://github.com/dusty-nv/jetson-containers/tree/master/packages/llm/huggingface_hub https://github.com/dusty-nv/jetson-containers/tree/master/packages/numpy https://github.com/dusty-nv/jetson-containers/tree/master/packages/audio/faster-whisper |
| Dockerfile | https://github.com/dusty-nv/jetson-containers/tree/master/packages/smart-home/wyoming/wyoming-whisper/Dockerfile |
| 镜像 | https://hub.docker.com/r/dustynv/wyoming-whisper/tags (2024-04-30, 5.2GB) |
| $ 说明 | 基于wyoming协议的faster-whisper,用于Home Assistant。基于https://github.com/home-assistant/addons/blob/master/whisper/Dockerfile |
| 仓库/标签 | 日期 | 架构 | 大小 |
| :-- | :--: | :--: | :--: | $ https://hub.docker.com/r/dustynv/wyoming-whisper/tags%60 | 2024-04-30 | arm64 | 5.2GB |
| https://hub.docker.com/r/dustynv/wyoming-whisper/tags | 2024-04-24 | arm64 | 5.2GB |
容器镜像与JetPack/L4T的其他次要版本兼容:
• L4T R32.7容器可在L4T R32.7的其他版本(JetPack 4.6+)上运行
• L4T R35.x容器可在L4T R35.x的其他版本(JetPack 5.1+)上运行
要启动容器,可以使用https://github.com/dusty-nv/jetson-containers/tree/master/docs/run.md和https://github.com/dusty-nv/jetson-containers/tree/master/docs/run.md#autotag,或手动组合docker run`命令:
bash# 自动拉取或构建兼容的容器镜像 jetson-containers run $(autotag wyoming-whisper) # 或显式指定上述容器镜像之一 jetson-containers run dustynv/wyoming-whisper:latest-r36.2.0 # 或使用'docker run' (指定镜像和挂载等) sudo docker run --runtime nvidia -it --rm --network=host dustynv/wyoming-whisper:latest-r36.2.0
https://github.com/dusty-nv/jetson-containers/tree/master/docs/run.md%E5%B0%86%E5%8F%82%E6%95%B0%E8%BD%AC%E5%8F%91%E7%BB%99%60docker run
,并添加一些默认值(如--runtime nvidia、挂载/data`缓存、检测设备)
https://github.com/dusty-nv/jetson-containers/tree/master/docs/run.md#autotag%E6%9F%A5%E6%89%BE%E4%B8%8E%E6%82%A8%E7%9A%84JetPack/L4T%E7%89%88%E6%9C%AC%E5%85%BC%E5%AE%B9%E7%9A%84%E5%AE%B9%E5%99%A8%E9%95%9C%E5%83%8F — 本地镜像、从仓库拉取的镜像或构建的镜像。
要将您自己的目录挂载到容器中,请使用-v或--volume标志:
bashjetson-containers run -v /主机路径:/容器路径 $(autotag wyoming-whisper)``` 要启动容器运行命令(而非交互式shell,请使用以下命令: ```bash jetson-containers run $(autotag wyoming whisper) my_app --abc xyz
可以将任何选项传递给docker run,它会在执行前打印出构建的完整命令。
如果如上所示使用autotag,它会在需要时提示您构建容器。要手动构建,请先完成https://github.com/dusty-nv/jetson-containers/tree/master/docs/setup.md%EF%BC%8C%E7%84%B6%E5%90%8E%E8%BF%90%E8%A1%8C%EF%BC%9A
bashjetson-containers build wyoming-whisper
上述依赖项将被构建到容器中,并在构建过程中进行测试。使用https://github.com/dusty-nv/jetson-containers/tree/master/jetson_containers/build.py%E8%8E%B7%E5%8F%96%E6%9E%84%E5%BB%BA%E9%80%89%E9%A1%B9%E3%80%82
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本,请访问 标签列表页面。
来自真实用户的反馈,见证轩辕镜像的优质服务