Bird Song
BirdNET-Pi is a real-time acoustic bird classification system designed for Raspberry Pi. It uses a USB sound card to pick up bird sounds and classifies them locally using a pre-trained machine learning model. I had enough electronics lying around to build this without buying anything.It creates a spectrogram of each recorded bird song.
I live on Prince Edward Island, Canada. There is a nice wooded area just outside my back door. We get lots of crows, seagulls and other species visiting.
Supplies
Raspberry Pi 4
USB Sound Card
Bird Box for the parts
Portable Power Pack
Install BirdNET Software
The best installation software can be found at Github
https://github.com/mcguirepr89/BirdNET-Pi/wiki/Installation-Guide
This is a fully detailed instructions that I am not going to reproduce.
You can download Raspberry Imager from Raspberry Pi Imager
Once it is installed and you place the SD card in the laptop you will see the image I have included.
Testing
You can experiment before you move your box to the outdoors. I have a Acer Laptop with Windows. I used You Tube to play bird sounds and it picked up a crow. One feature of this is to obtain a free key at Flickr to include a picture of the bird that you have captured it's song.