Show HN: PrivaKit – 基于 WebGPU 的零上传浏览器内 AI 工作空间
1 分•作者: felixne•4 个月前
大家好，我是开发者。
我意识到，对于敏感工作流程，例如转录董事会会议、OCR识别雇佣合同或清理身份证照片，使用云端AI API存在巨大的隐私风险。
因此，我使用transformers.js、Whisper和WebGPU构建了一个客户端工作区。所有操作都在本地运行。在初始模型加载后，您可以开启飞行模式，它仍然可以完美地转录和提取文本。
为了保持透明，我撰写了一份关于数据流（或者说，不流）的技术审计报告。我的唯一后端是一个位于新加坡的2核节点，运行自托管的Plausible分析：[<a href="https://gist.github.com/ygx2378/3275b333504c6a9def50ef531b548a26" rel="nofollow">https://gist.github.com/ygx2378/3275b333504c6a9def50ef531b54...</a>]
我还在学习基于浏览器的内存管理，所以非常希望得到您关于模型在您特定GPU上加载方式的反馈！
查看原文
Hi HN, I'm the builder.
I realized that using cloud AI APIs for sensitive workflows—like transcribing board meetings, OCRing employment contracts, or cleaning up ID photos—is a massive privacy liability.
So I built a client-side workspace using transformers.js, Whisper, and WebGPU. Everything runs locally. You can turn on Airplane Mode after the initial model load, and it still transcribes and extracts text perfectly.
To keep myself honest, I wrote a technical audit of how the data flows (or rather, doesn't flow). My only backend is a tiny 2-core node in Singapore running self-hosted Plausible analytics: [<a href="https://gist.github.com/ygx2378/3275b333504c6a9def50ef531b548a26" rel="nofollow">https://gist.github.com/ygx2378/3275b333504c6a9def50ef531b54...</a>]
I'm still learning the ropes of browser-based memory management, so I'd love your feedback on how the models load on your specific GPUs!