Tool · LREC-COLING 2024
GlotScript
A resource and tool for writing system identification.
Overview
GlotScript has two parts. GlotScript-R is a resource listing the writing systems used by more than 8,000 languages, compiled from Wikipedia, SIL and other sources. GlotScript-T is a Python library that detects the ISO 15924 script of any text and can separate mixed-script sentences, covering every script in Unicode.
Features
- Script detection with confidence scores
- Script separation for mixed text
- Language → script resource (core and auxiliary scripts)
- Up to date with recent Unicode versions