Offline browser app identifies bird species from calls using local AI

A developer has created a web application called Touch Grass Birder that identifies bird species from audio recordings entirely within a user's browser. The tool uses the open BirdNET v2.4 model to recognize 6,522 species and runs locally via ONNX Runtime WebAssembly, requiring no internet connection after initial setup. It is designed for situations where birdwatchers lack cellular service, enabling identification through a six-second recording. The application is fully open-source and prioritizes minimizing screen time by instructing users to immediately pocket their devices after receiving results.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.



Discussion (0)
Log in to join the discussion and vote.
Log in