#167167th of 168 in ML frameworks and libraries
ltp
Chinese NLP toolkit for word segmentation, POS tagging, NER and parsing
- Stars
- 5.3k
- License
- no license
- Last commit
- Mar 2026
- Last release
- Aug 2022
- Language
- Python
5,214 on 21 Apr 20265,267 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
LTP (Language Technology Platform) from HIT-SCIR runs six Chinese NLP tasks: word segmentation, POS tagging, named entity recognition, semantic role labeling, dependency parsing and semantic dependency parsing. It ships PyTorch multi-task models (Base, Small, Tiny) and a Rust perceptron "legacy" model limited to segmentation, POS and NER. Models download from Hugging Face and can be retrained with the provided scripts.
Who it is for: NLP researchers and developers processing Chinese text
Strengths
- Six Chinese NLP tasks through one Pipeline API on a shared pre-trained model
- Rust perceptron model: README claims 3.55x LTP3 speed, 17.17x with multithreading
- Training scripts and hydra configs allow training on private data
- Tiny, Small and Base models trade accuracy for speed; custom word lists supported
Weaknesses
- Commercial use requires a paid license; free only for academic and individual research
- No standard open-source license detected; terms are custom text in the README
- Last release is 2022-08
- Chinese only; legacy model covers just segmentation, POS and NER
What it needs
- GPU optional
- Needs PyTorch, Transformers, Hugging Face Hub
- Models: PyTorch, Hugging Face Hub, Rust perceptron (Avro)
Quick answers
Is ltp open source?
Its code is public on GitHub, but the repository has no license, so by default nobody may reuse it.
Does ltp need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in ML frameworks and libraries
See all 168| 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 | 93 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 training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |