G2P Frysk / G2P Nederlands
G2P Frysk and G2P Nederlands are web applications for converting Frisian and Dutch text to phonetic IPA transcriptions.
The following people were involved in the development of G2P Frysk: Wilbert Heeringa, Eduard Drenth (web service), Hans Van de Velde, Pieter Duijff, Jelske Dijkstra, Hindrik Sijens.
Data and models
As data sources the Frysk Hânwurdboek (edition 2016) and the Foarkarswurdlist were used. Two models were trained using Phonetisaurus: a larger model generating phonetic transcriptions without stress marks and a smaller model generating transcriptions with stress marks.
The larger model was trained on a dataset combining the Frysk Hânwurdboek and the Foarkarswurdlist, comprising 68,412 words in total. Since only the Frysk Hânwurdboek provides stress information in its orthographic entries, the smaller model was trained exclusively on this resource, comprising 62,244 words.
To incorporate stress information into the phonetic transcriptions, we used Phonetisaurus to align the orthographic forms with their corresponding phonetic transcriptions, allowing the stress marks to be transferred from the orthographic forms to the phonetic representations.
Who is involved
Wilbert Heeringa
Researcher
Wilbert Heeringa is a researcher at the Fryske Akademy, working on dialectometry, phonetics and statistics. He uses computational methods to measure dialect variation and change in vocabulary, morphology and pronunciation, and develops tools for phonetic research such as Visible Sounds.
Eduard Drenth
Software architect
Eduard Drenth is a software architect at the Fryske Akademy, where he is co-responsible for ICT policy . He is also involved in the Fryske Akademy’s language databases (Frysker) and the online Dutch-Frisian dictionary as a developer.
Hans Van de Velde
Researcher
Hans Van de Velde is a researcher in sociolinguistics at the Fryske Akademy. He studies language variation and change, multilingualism and phonetics, including the pronunciation of Frisian and Dutch in Fryslân, the evaluation of variations, and the development of experimental sociolinguistics.
Hindrik Sijens
Researcher
Hindrik Sijens is a researcher at the Fryske Akademy, specialising in lexicography, neologisms, databases and spelling in Frisian. He has worked on the Frisian dictionaries since 1985, including the Frysk Hânwurdboek, the Online Dutch–Frisian Dictionary and Frysker.
