Optimized
ONNX conversions of the
BSG – Finnish Birds Model, a pretrained bird sound classification model fine-tuned for Finland. The original model was developed at the
University of Jyväskylä and is based on the
BirdNET model architecture.
The original BSG model is distributed as a standalone classifier that expects pre-extracted BirdNET embeddings as input. The fused ONNX models in this repository merge BirdNET's feature extractor and the BSG classifier into a single end-to-end model that accepts raw spectrograms and outputs species predictions — identical to how the standard BirdNET ONNX model operates. This makes the BSG model a drop-in replacement for BirdNET in any application that supports custom ONNX models.
The ONNX models were converted from the original TFLite model and optimized for efficient inference using
birdnet-onnx-converter. ONNX enables deployment across a wide range of runtimes and hardware platforms including CPU, GPU, and edge devices via
ONNX Runtime.
The code for running inference with the model is available at:
luomus/bird-identificationFor building locally fine-tuned classifiers, see the BSG classifier builder:
plauha/BSG_classifier_builder1@article{nokelainen2024mobile,
2 title={A Mobile Application–Based Citizen Science Product to Compile Bird Observations},
3 author={Nokelainen, O. and Lauha, P. and Andrejeff, S. and H{\"a}nninen, J. and Inkinen, J. and Kallio, A. and Lehto, H.J. and Mutanen, M. and Paavola, R. and Schiestl-Aalto, P. and Somervuo, P. and Sundell, J. and Talaskivi, J. and Vallinm{\"a}ki, M. and Vancraeyenest, A. and Lehti{\"o}, A. and Ovaskainen, O.},
4 journal={Citizen Science: Theory and Practice},
5 volume={9},
6 number={1},
7 pages={24},
8 year={2024},
9 doi={10.5334/cstp.710}
10}
1@article{lauha2025bsg,
2 title={Bird Sounds Global - model builder: An end-to-end workflow for building locally fine-tuned bird classifiers},
3 author={Lauha, Patrik and Rannisto, Meeri and Somervuo, Panu and others},
4 journal={Authorea},
5 year={2025},
6 doi={10.22541/au.176599468.88578746/v1}
7}
This model was developed at the University of Jyväskylä. The ONNX conversion and optimization were performed independently to enable broader deployment options.
