Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Bangwa Warbler Acoustic Recogniser Data

Domain:

environment and energy

Record type:

datasetsoftwarepaper
Creator:
WinBud
Publisher:
Zenodo
Host:avatar

This dataset contains WAV recordings and PNG spectrograms of the African songbird Bangwa Warbler (Bradypterus bangwaensis). The PNG spectrograms were used to train and evaluate an automated ResNet18-based classifier, while the WAV recordings were used to create a custom BirdNET species‑specific model (BirdNET-Analyzer version). The dataset is organised into folders representing training, validation, and testing sets.

This dataset accompanies the publication: Winiarska, D., Budka, M. Reproducing a year‑round expert survey with deep learning.
 
Code for using the PNG dataset, including the full training and evaluation pipeline, is available at: dwiniarska/Bangwa-Warbler-A…
 
Folder structure:
 
PNG
│
├── training_thresholds/       # PNG sets used for training with reduced data
│
├── train/       # Training spectrograms (default 320 positive/960 negative)
│
├── val/       # Validation spectrograms 
│
└── test/       # Test set spectrograms
 
WAV
│
├── training_samples/       # 5-sec audio clips used for training
│
├── validation/       # 5-sec audio clips used for validation
│
└── test/       # 1-minute audio files for year-round inference

Visit

doi.org

Tasks

image classificationcomputer vision

Languages

Nda’nda’Ngemba

Licenses

info:eu-repo/semantics/openAccessCreative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

dwiniarska/Bangwa-Warbler-Acoustic-Recogniser

dwiniarska/Bangwa-Warbler-Acoustic-Recogniser

Binary spectrogram classifier for Bangwa Warbler vocalisations using a ResNet18 architecture. # Ban