Project: FIN-CLARIAH
Grant agreement: Academy of Finland no. 358720
Start date: 01-01-2024
Duration: 24 months
WP 1.2: Report on Transcription service for minority languages
Date of reporting: 24-11-2025
Report authors: Martin Matthiesen (CSC)
Contributors: Yaroslav Getman, Tamas Grosz (Aalto), Sam Hardwick (CSC)
Deliverable location: https://github.com/CSCfi/Kielipankki-utilities/tree/master/asr/apptainer
Keywords for the deliverable page: Finland-Swedish, Sámi
An Automatic Speech Recognition model for Northern Sámi (henceforth ”Sámi ASR model”) has been created at Aalto University. The model has been packaged into a container[2] at CSC, which may be used in the user’s preferred computing environment, and also in CSC’s Secure Desktop environment[3] for processing sensitive data.
The packaging process, which can be repurposed for other wav2vec models and/or models available via Huggingface[4] is documented in the Language Bank’s Github[5] repository.
At the time of writing the model for Finnish-Swedish is still under development at Aalto University. It will be packaged as soon as it becomes available.
[1] Sámi ASR model: https://huggingface.co/GetmanY1/wav2vec2-large-sami-cont-pt-22k-finetuned
[2] https://www.kielipankki.fi/tools/sami-asr/
[3] In SD Desktop the tool can be installed using the ”auto-apptainer” tool.
[4] https://en.wikipedia.org/wiki/Hugging_Face
[5] https://github.com/CSCfi/Kielipankki-utilities/tree/master/asr/apptainer
The FIN-CLARIAH project has received funding from the European Union – NextGenerationEU instrument and is funded by the Research Council of Finland under grant number 358720.
