kermitt2/delft
a Deep Learning Framework for Text https://delft.readthedocs.io/
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.
Stars
415
Forks
66
Language
Python
License
Apache-2.0
Category
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.
Related frameworks
yoeo/guesslang
Detect the programming language of a source code
matthewdeanmartin/whats_that_code
detect programming language of source in pure python from an ensemble of classifiers
airalcorn2/Deep-Semantic-Similarity-Model
My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent...
christiansafka/img2vec
:fire: Use pre-trained models in PyTorch to extract vector embeddings for any image
microsoft/NeuronBlocks
NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego