2026-09-18
Bacpipe: A Python package to make bioacoustic deep learning models accessible
Publication
Publication
Methods in Ecology and Evolution , Volume 2026
- Natural sounds have been recorded for millions of hours over the previous dec-ades using passive acoustic monitoring. Improvements in deep learning modelshave vastly accelerated the analysis of large portions of this data. While newmodels advance the state-of-the-art, accessing them using tools to harness theirfull potential is not always straightforward.
2. Here we present bacpipe, a collection of bioacoustic deep learning models andevaluation pipelines accessible through a graphical and programming interface,designed for both ecologists and computer scientists.
3. Bacpipe streamlines the usage of state-of-the-art models on custom audio data-sets, generating acoustic feature vectors (embeddings) and classifier predictions.A modular design allows evaluation and benchmarking of models through interac-tive visualizations, clustering and probing.
4. We believe that access to new deep learning models is important. By designingbacpipe to target a wide audience, researchers will be enabled to answer newecological and evolutionary questions in bioacoustics
| Additional Metadata | |
|---|---|
| , , , , , , | |
| doi.org/10.1111/2041-210x.70406 | |
| Methods in Ecology and Evolution | |
| Released under the CC-BY 4.0 (“Attribution 4.0 International”) License | |
| Organisation | Staff publications |
|
Kather, Vincent S., Haupert, Sylvain, Ghani, Burooj& Stowell, D. (2026). Bacpipe: A Python package to make bioacoustic deep learning models accessible. Methods in Ecology and Evolution, 2026.https://doi.org/10.1111/2041-210x.70406 |
|
