metadata
datasets:
- NatLibFi/Finna-metadata
language:
- fi
- sv
- en
license: cc0-1.0
pipeline_tag: text-classification
tags:
- glam
- lam
- subject indexing
- annif
thumbnail: >-
https://raw.githubusercontent.com/NatLibFi/FintoAI/main/ai.finto.fi/static/img/finto-ai-social.png
FintoAI-data-YSO
This repository is for the Annif projects with the
YSO vocabulary
used at the Finto AI service.
The current models were published there 2026-06-11.
The models have been trained on Python 3.11.13 with Annif version 1.4.1.
The configurations of the projects are in individual .cfg files in the root of
this repository.
The GitHub repository FintoAI-data-YSO contains the project configurations and the DVC pipeline used in training and evaluating the projects.
The training corpora that are public can be found from the Annif-corpora repository.
Usage
To download selected projects with Annif use the annif download command, for
example run
annif download "*-fi" NatLibFi/FintoAI-data-YSO
See Annif wiki for more information.
Projects
Project ID Project Name Vocabulary ID Language
---------------------------------------------------------------------------
yso-bonsai-en YSO Omikuji Bonsai English yso en
yso-bonsai-fi YSO Omikuji Bonsai Finnish yso fi
yso-bonsai-sv YSO Omikuji Bonsai Swedish yso sv
yso-en YSO English (2026.3.Maimonides) yso en
yso-fasttext-en YSO fastText English yso en
yso-fasttext-fi YSO fastText Finnish yso fi
yso-fasttext-sv YSO fastText Swedish yso sv
yso-fi YSO suomi (2026.3.Maimonides) yso fi
yso-mllm-en YSO MLLM English yso en
yso-mllm-fi YSO MLLM Finnish yso fi
yso-mllm-sv YSO MLLM Swedish yso sv
yso-sv ALLFO svenska (2026.3.Maimonides) yso sv