OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Hazm

Hazm is a Python library for natural-language processing of Persian text, with tools for normalization, tokenization, lemmatization, part-of-speech tagging, chunking, dependency parsing, embeddings and reading Persian corpora.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hazm — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Hazm when a Python project needs multiple Persian NLP stages, from normalization and tokenization through linguistic analysis or embeddings.

Who it is for

  • Python developers building Persian text-processing pipelines
  • Teams adding Persian linguistic analysis or embeddings to text applications

Documented uses

  • Standardize Persian text, including diacritics and zero-width non-joiner usage.
  • Split Persian text into sentences and words.
  • Reduce words to base forms and assign part-of-speech tags.
  • Identify phrase chunks and syntactic dependency relations.
  • Create word and sentence embeddings or read popular Persian corpora.
Before you choose

Requirements & limits

The public repository specifies an MIT license. The README lists Python 3.12 or later as the installation requirement.

  • Hazm is a library to use in Python projects, rather than a standalone text-analysis interface.
  • Pretrained models are downloaded from Hugging Face; using them requires huggingface-hub and model identifiers.
  • The repository reports evaluation results for selected modules, which may help assess components but do not establish performance for a reader's own data.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Hazm for a Persian text workflow

Install the library and prepare its documented pretrained-model dependency.

Before you start

  • Python 3.12 or later
  • pip
  • The huggingface-hub package when using pretrained models

Steps

  1. Install Hazm with pip install hazm.

  2. For pretrained models, install huggingface-hub with pip install huggingface-hub.

  3. Select a model repository ID and filename for the component you plan to use.

Expected outcome

Hazm and, if needed, its Hugging Face model-download dependency are installed; the README describes supplying model IDs and filenames for pretrained components.

Guide limitations

  • The installation instructions do not constitute a run or deployment guide.
  • A model repository ID and filename are needed to use pretrained models.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
roshan-research/hazm · Official homepage title · retained in its source language
How we review sourcesSuggest a correction