livingingroups/animal2vec

animal2vec: A self-supervised transformer for rare-event raw audio input

45
/ 100
Emerging

This project helps bioacoustic researchers analyze large audio datasets for rare animal vocalizations. It takes raw, unlabeled audio recordings, learns patterns from them, and then uses a small amount of labeled data to identify specific animal calls. Scientists, conservationists, and ecologists can use this to efficiently process vast amounts of acoustic data to understand animal behavior or monitor populations.

Use this if you need to detect infrequent animal sounds within extensive audio recordings, especially when you have limited labeled examples for training.

Not ideal if you are working with non-audio data, or if your primary goal is real-time detection on edge devices with very limited computational resources.

bioacoustics wildlife-monitoring conservation-research animal-behavior soundscape-ecology
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

30

Forks

7

Language

Python

License

MIT

Last pushed

Dec 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/livingingroups/animal2vec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.