Touch Grass — A Bird ID App That Works When There's No Signal

说明与用途

Touch Grass 是一个 PWA，使用开放权重 AI 模型在设备上完全离线识别鸟类、植物和昆虫，保障用户隐私。

问题

Identifying bird calls typically requires uploading audio to a cloud API, exposing location and usage data.

结果

The app enables quick, private bird identification offline, preserving user privacy and allowing use in low‑signal environments.

工作流

• Record a 3‑second audio clip
• Convert clip to a mel spectrogram locally
• Run BirdNET‑ONNX model in a Web Worker
• Return species prediction without any network call

证据

Touch Grass is a Progressive Web App that runs open‑weight AI models entirely inside the browser.

来源

Record 3-second audio clips, identify species via BirdNET‑ONNX (~20MB, quantized, 3000+ species), all on‑device.

来源

After initial model downloads, no internet required. Service worker caches the app shell; IndexedDB stores observations and model cache.

来源