BirdBuddy: an offline bird call identifier that runs entirely on your device

Описание и применение

BirdBuddy — автономное приложение для идентификации звуков птиц, работающее полностью на устройстве без подключения к интернету, используя модели BirdNET, Piper и Qwen3.5‑4B.

Задача

Hikers and birders need to identify bird calls in remote locations without internet access.

Результат

BirdBuddy delivers offline bird call identification with a 52 MB classifier and 63 MB TTS voice, achieving <2 s inference latency on a laptop CPU and no external dependencies.

Рабочий процесс

• Open the app
• Tap once to record a 3‑second bird call
• The app runs BirdNET ONNX inference locally
• Piper TTS speaks the top match
• Optional: adjust Top‑K, confidence threshold, or voice speed in Settings

Доказательства

BirdBuddy tells you what it is — with everything running locally on the device in your pocket.

Источник

The identification finishes in about two seconds. No cloud round‑trip, no account, no upload.

Источник

I used the FP32 truncated‑DFT ONNX variant (~52 MB) running through ONNX Runtime on CPU.

Источник

Piper speaks it out loud: "I heard a Northern Cardinal."

Источник

I built a 165‑example chat dataset covering 60 common North American species, then fine‑tuned Qwen3.5‑4B with a LoRA adapter (r=16) using Tinker.

Источник

Copilot was the workbench for the entire project

Источник