Voxaboxen
Acoustic classification
Call Identification
Package or Library
Voxaboxen is a deep learning framework designed to find the start and stop times of (possibly overlapping) sound events in a recording.
| Model metadata | Value |
|---|---|
| Tool Type | Package or Library |
| Broad Task | Acoustic classification |
| Specific Task | Call Identification |
| Model type | AVES, Transformer |
| Description | Voxaboxen is a deep learning framework designed to find the start and stop times of (possibly overlapping) sound events in a recording. |
| Task Specific | Yes |
| Ecology Specific | Yes |
| Language(s) | Python |
| Last Edited Time | 6/21/24 10:24 |
| Related Publication(s) | https://doi.org/10.5281/zenodo.8381019 |
| Dependencies | PyYAML, einops, intervaltree, librosa, matplotlib, mir_eval, numpy, pandas, plumbum, pytorch, scipy, seaborn, soundfile, torchaudio, tqdm |
| Tool URL (Github etc.) | https://github.com/earthspecies/voxaboxen |
| Last Update (time ago) | Last updated within 6 months |
| License | AGPL-3.0 |
| Contact Name | Benjamin Hoffman |
| Contact Email | mailto:benjamin@earthspecies.org |
| Contact Responsiveness | Very responsive |
| HuggingFace URL | nan |
| Reproducibility Method | nan |