acoupi-birdnet 0.1.1

An acoupi-compatible BirdNET model implementation

acoupi_birdnet

An acoupi-compatible BirdNET model and program

[!TIP] Read the latest documentation

Readme Content

• What is acoupi_birdnet?
• What is the difference between acoupi and acoupi_birdnet
• Requirements
• Installation
• What is acoupi?

What is acoupi_birdnet?

acoupi_birdnet is an open-source Python package that implement the BirdNET-Analyzer bioacoustic deep-learning model on edge devices like the Raspberry Pi, using the acoupi framework. The BirdNET-Analyzer DL model has been developed by the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology in collaboration with Chemnitz University of Technology to detect and classify more than 6000 bird species.

What is the difference between acoupi and acoupi_birdnet?

acoupi_birdnet and acoupi are different. The acoupi_birdnet program is built on top of the acoupi python package. Think of acoupi like a bag of LEGO pieces that you can assemble into multiple shapes and forms. acoupi_birdnet would be the results of assembling some of these LEGO pieces into "birds"!

[!TIP] Get familiar with acoupi

acoupi_birdnet builds on and inherits features from acoupi. If you want to learn more the acoupi framework, we recommand starting with acoupi's home documentation.

Requirements

acoupi has been designed to run on single-board computer devices like the Raspberry Pi (RPi). Users should be able to download and test acoupi software on any Linux-based machines with Python version >=3.8,<3.12 installed.

• A Linux-based single board computer such as the Raspberry Pi 4B.
• A SD Card with 64-bit Lite OS version installed.
• A USB microphone, such as an AudioMoth USB Microphone or a Lavalier.

[!TIP] Recommended Hardware

The software has been extensively developed and tested with the RPi 4B. We advise users to select the RPi 4B or a device featuring similar specifications.

Installation

To install acoupi_birdnet on your embedded device, you will need to first have acoupi installed on your device. Follow these steps to install both acoupi and acoupi_birdnet:

Step 1: Install acoupi and its dependencies.

curl -sSL https://github.com/acoupi/acoupi/raw/main/scripts/setup.sh | bash

Step 2: Install acoupi_birdnet and its dependencies

pip install acoupi_birdnet

Step 3: Configure the acoupi_birdnet program.

acoupi setup --program acoupi_birdnet.program

Step 4: Start the acoupi_birdnet program.

acoupi deployment start

[!TIP] To check what are the available commands for acoupi, enter acoupi --help.

What is acoupi?

acoupi is an open-source Python package that simplifies the use and implementation of bioacoustic classifiers on edge devices. It integrates and standardises the entire bioacoustic monitoring workflow, facilitating the creation of custom sensors, by handling audio recordings, processing, classifications, detections, communication, and data management.

[!WARNING] Licenses and Usage

acoupi_birdnet can not be used for commercial purposes.

The acoupi_birdnet program inherits the BirdNET-Analyzer model license, published under the Creative Commons Attribution-NonCommercial 4.0 International. Please make sure to review this license to ensure your intended use complies with its terms.

[!WARNING] Model Output Reliabilit

Please note that acoupi_birdnet program is not responsible for the accuracy or reliability of predictions made by the BirdNET-Analyzer model. It is essential to understand the model's performance and limitations before using it in your project.

For more details on the BirdNET model, refer to the publication Kahl S., et al., (2021) BirdNET: A deep learning solution for avian diversity monitoring. To learn more about using the BirdNET scores and outputs from the model, refer to Wood CM. and Kahl S., (2024) Guidelines for appropriate use of BirdNET scores and other detector outputs.

[!IMPORTANT] We would love to hear your feedback about the documentation. We are always looking to hearing suggestions to improve readability and user's ease of navigation. Don't hesitate to reach out if you have comments!