Pretrained models for animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics

Dataset

DOI

Model weights for animal2vec Please find the accompanying code at our official repository: github.com/livingingroups/animal2vec Here you find the model weights for the pretrained and the finetuned animal2vec model using the MeerKAT dataset. For more information on how to use this, please see our paper and our GitHub repository.

Identifier
DOI	https://doi.org/10.17617/3.ETPUKU
Metadata Access	https://edmond.mpg.de/api/datasets/export?exporter=dataverse_json&persistentId=doi:10.17617/3.ETPUKU

Provenance
Creator	Schaefer-Zimmermann, Julian; Demartsev, Vlad; Averly, Baptiste; Dhanjal-Adams, Kiran; Duteil, Mathieu; Gall, Gabriella; Faiß, Marius; Johnson-Ulrich, Lily; Stowell, Dan; Manser, Marta; Roch, Marie; Strandburg-Peshkin, Ariana
Publisher	Edmond
Publication Year	2024
OpenAccess	true
Contact	jzimmermann(at)ab.mpg.de

Representation
Language	English
Resource Type	Dataset
Version	1
Discipline	Other