stanza
A Python NLP Library for Many Human Languages, by the Stanford NLP Group
Decision gist · record as of 2026-08-14
Yes. Stanza is actively maintained, has no known vulnerabilities, installs with low friction, and is permissively licensed. It's the standard choice for researchers and developers needing accurate, out-of-the-box multilingual NLP. Install it if you need dependency parsing, NER, or POS tagging across many languages or in biomedical domains; skip it only if you need real-time performance on resource-constrained systems or prefer a lighter-weight alternative.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later.
- PyTorch 1.3.0+ must be installed (typically resolved by pip).
- Models are downloaded on first use or via explicit stanza.download() call.
License · maintenance · safety
Apache License 2.0 (permissive) — Apache License 2.0 (permissive) allows commercial and private use with minimal restrictions, making it suitable for most production and research applications.
last release 2026-07-15 (30 days) · last repo commit 2026-08-14 · 7,861 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,116,772 downloads/mo, #4,349 on PyPI
Alternatives
Verify before relying
pip install stanza
import stanza
stanza.download('en')
nlp = stanza.Pipeline('en')
doc = nlp("Barack Obama was born in Hawaii.")
print(doc.sentences[0].print_dependencies())- Performance characteristics (speed, memory usage) for large-scale document processing across different languages
- Exact model download size and storage requirements for the 60+ supported languages
- Compatibility and integration details with the Java Stanford CoreNLP backend beyond basic setup
What it is and what it does
Stanza is Stanford NLP Group's official Python library for multilingual natural language processing. It provides a neural pipeline for core NLP tasks—tokenization, lemmatization, part-of-speech tagging, dependency parsing, and named entity recognition—across 60+ languages. The library also wraps Java Stanford CoreNLP for users who need additional capabilities. Biomedical and clinical English models are available for domain-specific work in medical text and literature.
The package depends on PyTorch for its neural components, along with supporting libraries like numpy, networkx, requests, and huggingface-hub for model management. Installation is straightforward via pip, and models auto-download on first pipeline use. It's designed for researchers, developers, and production systems that need accurate, language-agnostic NLP without building models from scratch.
Use it for
- Extract grammatical structure and named entities from documents in multiple languages for information extraction pipelines
- Analyze syntactic dependencies in biomedical literature or clinical notes for domain-specific NLP tasks
- Build multilingual chatbots or question-answering systems that require tokenization and semantic understanding
- Process non-English text in research projects where language support across 60+ languages is needed
- Integrate with Java CoreNLP workflows from Python for advanced linguistic analysis or custom rule-based processing
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Stanza is actively maintained, has no known vulnerabilities, installs with low friction, and is permissively licensed. It's the standard choice for researchers and developers needing accurate, out-of-the-box multilingual NLP. Install it if you need dependency parsing, NER, or POS tagging across many languages or in biomedical domains; skip it only if you need real-time performance on resource-constrained systems or prefer a lighter-weight alternative.
Install
stanza on PyPI
Before you install
Low friction installation via pip with wheel distribution. Active maintenance—last release 30 days ago, repository updated 2026-08-14, 7861 stars. Requires PyTorch 1.3.0 or above as a core dependency alongside 10 other runtime packages.
Requires Python 3.9 or later. PyTorch 1.3.0+ must be installed (typically resolved by pip). Models are downloaded on first use or via explicit stanza.download() call.
License in practice
Apache License 2.0 (permissive) allows commercial and private use with minimal restrictions, making it suitable for most production and research applications.
Quickstart
pip install stanza
import stanza
stanza.download('en')
nlp = stanza.Pipeline('en')
doc = nlp("Barack Obama was born in Hawaii.")
print(doc.sentences[0].print_dependencies())Verify before relying
- Performance characteristics (speed, memory usage) for large-scale document processing across different languages
- Exact model download size and storage requirements for the 60+ supported languages
- Compatibility and integration details with the Java Stanford CoreNLP backend beyond basic setup
Package facts
| License | Apache License 2.0 permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 11 packagesemojinumpyplatformdirsprotobufrequestsnetworkxtomlitorchtqdmudtoolshuggingface-hub |
| Maintenance | Actively maintained 30 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,116,772 / month, #4,349 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Information TechnologyIntended Audience :: Science/ResearchProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: Information AnalysisTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Text ProcessingTopic :: Text Processing :: Linguistic |
Evidence: stanza-1.14.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “multilingual NLP pipeline”
- stanzaStanza is a Python NLP library that runs accurate natural language…
- polyglotPolyglot is a multilingual natural language processing pipeline that…
- spacy-language-detectionAdds language detection to spaCy pipelines at document and sentence…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also spacy · urduhack · nltk · ginza · polyglot · gliner · minisbd · ja-ginza · flair · spark-nlp