------------------------------------------------------------------------------- Faroese G2P Models ------------------------------------------------------------------------------- Authors : Carlos Daniel Hernández Mena, Sandra Saxov Lamhauge, Iben Nyholm Debess, Annika Simonsen. Language : Faroese. Recommended use : speech recognition. ------------------------------------------------------------------------------- Description ------------------------------------------------------------------------------- The "Faroese G2P Models" is a set of two models trained with the software tool "Sequitur-G2P" [1] which is a trainable grapheme-to-phoneme tool developed at RWTH Aachen University (https://www.rwth-aachen.de/) by Maximilian Bisani. One of the models is for Central Faroese and the other is for the East variant. The set also includes two files with the corresponding repertory of phonemes for the Central (central.phones) and the East (east.phones) variants. Instructions of how to install and use Sequitur-G2P can be found in the official Pypi repository. Just type in any web browser the keywords: "sequitur-g2p pypi" to find it. ------------------------------------------------------------------------------- Citation ------------------------------------------------------------------------------- When publishing results based on the models, please refer to: Hernández Mena, Carlos Daniel; Lamhauge, Sandra Saxov; Nyholm Debess, Iben; Simonsen, Annika. "Faroese G2P Models". Web Download. Reykjavik University: Language and Voice Lab, 2022. Contact: Carlos Daniel Hernández Mena (carlos.mena@ciempiess.org) License: CC BY 4.0 ------------------------------------------------------------------------------- Acknowledgements ------------------------------------------------------------------------------- The authors want to thank to Jón Guðnason, head of the Language and Voice Lab for providing computational power to make these models possible. We also want to thank to the "Language Technology Programme for Icelandic 2019-2023" which is managed and coordinated by Almannarómur, and it is funded by the Icelandic Ministry of Education, Science and Culture. Special thanks to The Ravnur Project for making their "Basic Language Resource Kit"(BLARK 1.0) publicly available through the research paper "Creating a Basic Language Resource Kit for Faroese" https://aclanthology.org/2022.lrec-1.495.pdf ------------------------------------------------------------------------------- References ------------------------------------------------------------------------------- [1] Bisani, M., & Ney, H. (2008). Joint-sequence models for grapheme-to-phoneme conversion. Speech communication, 50(5), 434-451. GitHub: https://github.com/sequitur-g2p/sequitur-g2p ------------------------------------------------------------------------------- -------------------------------------------------------------------------------