#7070th of 105 in ML frameworks and libraries
stanza
Python NLP toolkit for tokenizing, tagging and parsing text in 60+ languages
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7.9k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
7,718 on 1 Apr 20267,904 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Stanza is the Stanford NLP Group's Python library with a PyTorch neural pipeline for tokenization, multi-word token expansion, POS and morphological tagging, lemmatization, Universal Dependencies parsing and NER. It also includes a wrapper for calling the Java Stanford CoreNLP software from Python. Biomedical and clinical English model packages are available.
Who it is for: NLP researchers and engineers needing multilingual linguistic analysis in Python
Strengths
- Models for 60+ languages, covering all Universal Dependencies v2.8 treebanks
- Each neural module can be retrained on your own CoNLL-U or BIOES data
- Official Python client for Java CoreNLP, including Semgrex and Ssurgeon
- Separate biomedical and clinical English models for syntax and NER
Weaknesses
- Training is not supported through the Pipeline interface; requires a source checkout
- Per-sentence calls are slow; documents must be concatenated and batched manually
- NER models exist only for a few widely spoken languages
- CoreNLP use needs a separate Java download and CORENLP_HOME setup
What it needs
- GPU optional
- Needs PyTorch, Stanford CoreNLP (Java, optional)
- Models: Universal Dependencies treebank models, NER models, Biomedical and clinical English models
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |