Hironsan/HateSonar

Hate Speech Detection Library for Python.

53
/ 100
Established

Provides pre-trained classification across three categories (hate speech, offensive language, neither) with confidence scores for each, eliminating the need for model training. Uses a BERT-based architecture for semantic understanding of text toxicity. Offers a simple API (`Sonar.ping()`) that returns structured predictions with per-class confidence distributions.

193 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

193

Forks

38

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Hironsan/HateSonar"

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