nlp-uoregon/trankit
Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
This tool helps researchers and data scientists automatically process text in over 100 languages. You input raw text or pre-segmented sentences, and it outputs structured linguistic information like identified words, parts of speech, and grammatical relationships. It's designed for anyone working with multilingual text data who needs accurate and efficient linguistic analysis.
791 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to quickly and accurately break down text in many different languages into its core linguistic components for further analysis.
Not ideal if you primarily work with a single language and already have highly specialized tools for very niche NLP tasks.
Stars
791
Forks
106
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 22, 2025
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/nlp-uoregon/trankit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
UBC-NLP/turjuman
TURJUMAN, a neural toolkit for translating from 20 languages into Modern Standard Arabic (MSA).
sagorbrur/codeswitch
CodeSwitch is a NLP tool, can use for language identification, pos tagging, name entity...
nusnlp/esc
The official code of the "Frustratingly Easy System Combination for Grammatical Error Correction" paper
nusnlp/greco
The official code for the "System Combination via Quality Estimation for Grammatical Error...
mynlp/pnmt
Pre-train support for OpenNMT (PNMT)