#language-detection #language-recognition

lingua-telugu-language-model

The Telugu language model for Lingua, an accurate natural language detection library

5 stable releases

Uses new Rust 2024

new 1.3.0 Mar 9, 2026
1.2.0 Mar 20, 2025
1.1.0 Jun 13, 2023
1.0.1 Feb 16, 2022
1.0.0 Nov 21, 2020

#2262 in Text processing

Download history 3987/week @ 2025-11-17 4267/week @ 2025-11-24 4130/week @ 2025-12-01 4030/week @ 2025-12-08 10408/week @ 2025-12-15 8426/week @ 2025-12-22 7472/week @ 2025-12-29 15096/week @ 2026-01-05 14971/week @ 2026-01-12 21718/week @ 2026-01-19 17891/week @ 2026-01-26 36954/week @ 2026-02-02 54482/week @ 2026-02-09 61413/week @ 2026-02-16 87110/week @ 2026-02-23 93576/week @ 2026-03-02

301,406 downloads per month
Used in 2 crates (via lingua)

Apache-2.0

320KB
827 lines

Telugu language model for Lingua

This is the language model for the Telugu language which is used by Lingua, the most accurate natural language detection library in the Rust ecosystem.

Changelog

Version 1.3.0

  • The language model files have been converted into a new storage format. They are now stored as finite-state transducers (FSTs) which reduces memory consumption drastically at the cost of a slightly slower runtime performance.

Version 1.2.0

  • The language model has been enhanced by including unique and most common ngrams to support an absolute confidence metric which is independent of other languages.

Version 1.1.0

  • The language model files are now compressed with the Brotli algorithm which reduces the file size by 15 %, on average.

Dependencies