kermitt2/delft

a Deep Learning Framework for Text https://delft.readthedocs.io/

66
/ 100
Established

This is a framework that helps natural language processing (NLP) experts and researchers analyze and categorize text data. You input text, which can include rich layout information from documents like PDFs or HTML, and it outputs labeled sequences (e.g., identifying names) or classifications (e.g., categorizing comments). This tool is for data scientists, NLP engineers, and researchers who build and evaluate text-based AI models.

415 stars. Available on PyPI.

Use this if you need to build, test, and deploy deep learning models for sequence labeling or text classification, especially when dealing with text from complex documents containing layout information.

Not ideal if you are looking for a pre-trained, ready-to-use application and do not have expertise in deep learning, Python, or TensorFlow.

natural-language-processing text-classification information-extraction document-analysis deep-learning-research
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

415

Forks

66

Language

Python

License

Apache-2.0

Last pushed

Mar 08, 2026

Commits (30d)

0

Dependencies

20

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kermitt2/delft"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.