pemistahl/lingua-py

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

56
/ 100
Established

Combines rule-based and statistical Naive Bayes classification without neural networks or external dependencies, enabling fully offline detection. Backed by compiled Rust bindings for performance and minimal memory footprint while supporting 75 languages with specialized accuracy on short text. Suitable for NLP preprocessing pipelines including text classification, email routing, and spell checking applications.

1,659 stars. Actively maintained with 4 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

1,659

Forks

57

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/pemistahl/lingua-py"

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