MalteHB

-l-ctra

Ælæctra was created as part of a Cognitive Science bachelor thesis, in the attempt to enhance the Danish NLP community with a more efficient Transformer-based language model.

stedsans

language_analytics_cds

Repository for the course Language Analytics as part of the bachelor's tilvalg in Cultural Data Science at Aarhus University.

HearSay

Automatic rumour veracity classification of tweets

spatial_analytics_cds

super_secret_project

For now this is a super secret project.

visual_analytics_cds

Repository for the course Visual Analytics as part of the bachelor's tilvalg in Cultural Data Science at Aarhus University.

DaCy

DaCy: The State of the Art Danish NLP pipeline using SpaCy

danish_legal_lms

Danish Legal Language Models

danlp

DaNLP is a repository for Natural Language Processing resources for the Danish Language.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

datefinder

Find dates inside text using Python and get back datetime objects

langchain

⚡ Building applications with LLMs through composability ⚡

PKG-Cutter

No-brainer template for creating minimalistic Python packages 💪📦

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.