wikimedia/sentencex
A sentence segmentation library with wide language support optimized for speed and utility.
This tool helps language practitioners quickly and accurately split large blocks of text into individual sentences across many different languages. You provide a continuous block of text in a specific language, and it outputs a list of separate sentences, preserving original formatting. This is ideal for linguists, researchers, or data scientists working with multi-language textual data.
115 stars and 80,586 monthly downloads.
Use this if you need a fast and reliable way to break down long texts into sentences for tasks like preparing data for machine translation or text-to-speech systems.
Not ideal if you require extremely nuanced linguistic precision that accounts for every rare edge case, as this tool prioritizes speed and general accuracy over absolute, complex grammatical correctness.
Stars
115
Forks
11
Language
Rust
License
MIT
Category
Last pushed
Mar 16, 2026
Monthly downloads
80,586
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/wikimedia/sentencex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
PyThaiNLP/nlpo3
Thai natural language processing library in Rust, with Python and Node bindings.
forzagreen/n2words
Convert numerical numbers to written numbers, in 52+ languages.
greyblake/whatlang-rs
Natural language detection library for Rust. Try demo online: https://whatlang.org/
pemistahl/lingua-rs
The most accurate natural language detection library for Rust, suitable for short text and...
quickwit-oss/whichlang
A blazingly fast and lightweight language detection library for Rust