license: cc0-1.0
language:
- fi
pipeline_tag: text-classification
thumbnail: >-
https://raw.githubusercontent.com/NatLibFi/FintoAI/main/ai.finto.fi/static/img/finto-ai-social.png
tags:
- glam
- lam
- subject indexing
- annif
FintoAI-data-KAUNO
This repository is for the Annif projects with the KAUNO vocabulary used at the Finto AI service. The current models were published there 2023-12-04. The models have been trained on Python 3.8.10 with Annif version 1.0.0. See projects.toml for the configurations of the models.
This repository is mirrored from GitHub to the 🤗 Hugging Face Hub; the GitHub repository does not contain the model files, but only the configurations for the projects and the DVC pipeline, see below.
The training corpora that are public can be found from the Annif-corpora repository.
Models
The downloadable directories for projects and vocabularies are stored in the
/data
directory of this repository in the 🤗 Hugging Face Hub.
DVC pipeline
The projects are trained and evaluated using a DVC (Data Version Control) pipeline defined in dvc.yaml.
The pipeline takes care of
- installing Annif in a venv,
- loading the vocabulary,
- training the projects,
- evaluating the projects.
When the necessary vocabulary and training corpora are in place the pipeline can be run using the command
dvc repro
For more information about using DVC with Annif projects see the DVC exercise of Annif tutorial.