Custom Machine Learning Models with BirdNET Analyzer GUI

Custom Machine Learning Models with BirdNET Analyzer GUI is a recording of the BioacousTalks presentation from September 19th, 2023, presented by Stefan Kahl, the BirdNET team lead at Technische Universität Chemnitz and the Yang Center.

In this presentation, Stefan Kahl discusses advances in BirdNET, feature embeddings, and transfer learning. Then, he does a demo of the BirdNET Analyzer GUI and demos how we can use this tool to create custom models.

 0:00 Introduction

1:18 BirdNET+

5:13 Real-time Acoustic Monitoring

9:30 BirdNET Open-Source

12:11 Feature embeddings

19:53 Examples of using feature embeddings

25:03 Training your own models

27:51 Demo: Install and run the BirdNET Analyzer GUI

34:52 Demo: Train model

39:34 Demo: Run model on multiple files

43:05 Adding a noise folder 47:30 Roadmap for BirdNET GUI

50:30 Demo: Re-run improved model on multiple files

52:35 Demo: Evaluate detections

55:15 Provide feedback

Related Links

Access the BirdNET Analyzer GUI via this link: https://github.com/kahst/BirdNET-Analyzer

A step-by-step guide for acoustic analysis with BirdNET (including two demo datasets) is available here: https://zenodo.org/record/8357176

This tool is under active development. If you have recommendations for improvements or have spotted bugs in the program, please submit an “issue” on this page: https://github.com/kahst/BirdNET-Analyzer/issues