roshan-research/hazm
Persian NLP Toolkit
Comprises modular pipelines for normalization, tokenization, lemmatization, POS tagging, dependency parsing, and word/sentence embeddings. Integrates with Hugging Face Hub for automatic model downloading and caching, enabling seamless access to pretrained Persian models. Includes spaCy-compatible components and utilities for reading standard Persian corpora datasets.
1,381 stars and 3,129 monthly downloads. Used by 2 other packages. Available on PyPI.
Stars
1,381
Forks
205
Language
Python
License
MIT
Category
Last pushed
Dec 21, 2025
Monthly downloads
3,129
Commits (30d)
0
Dependencies
11
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/roshan-research/hazm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Dadmatech/DadmaTools
DadmaTools is a Persian NLP tools developed by Dadmatech Co.
amirivojdan/shekar
Simplifying Persian NLP for Modern Applications
GlobalMaksimum/sadedegel
A General Purpose NLP library for Turkish
GKalliatakis/Keras-VGG16-places365
Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification
NC0DER/KeyphraseExtraction
Keyphrase Extraction Review