A fast, extensible desktop translation suite. Translate, OCR, TTS, spell check — with a plugin system.
$ git clone https://github.com/ahatem/QTranslate.git▲ +1 ★ this week
Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
▲ +4 ★ this week
A multilingual morphological analysis library.
▲ +1 ★ this week
数据标注是一款专门对文本数据进行处理和标注的工具，通过简化快捷的文本标注流程和动态的算法反馈，支持用户快速标注关键词并能通过算法持续减少人工标注的成本和时间。数据标注的过程先由人工标注构建基础，再由自动标注反哺人工标注，最后由人工标注进行纠偏，从而大幅度提高标注的精准度和高效性。数据标注需要依赖开源的数字底座进行人员岗位管控。
▲ +2 ★ this week
The fast scanner generator for Java™ with full Unicode support
Code for Zero-Shot Tokenizer Transfer
The Libre Multilingual Analyzer, a Natural Language Processing (NLP) C++ toolkit.
Data from GitHub · snapshot Nov 13, 2026