English

Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges

Computation and Language 2024-02-06 v1

Abstract

This article introduces NB-Whisper, an adaptation of OpenAI's Whisper, specifically fine-tuned for Norwegian language Automatic Speech Recognition (ASR). We highlight its key contributions and summarise the results achieved in converting spoken Norwegian into written forms and translating other languages into Norwegian. We show that we are able to improve the Norwegian Bokm{\aa}l transcription by OpenAI Whisper Large-v3 from a WER of 10.4 to 6.6 on the Fleurs Dataset and from 6.8 to 2.2 on the NST dataset.

Cite

@article{arxiv.2402.01917,
  title  = {Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges},
  author = {Per E Kummervold and Javier de la Rosa and Freddy Wetjen and Rolv-Arild Braaten and Per Erik Solberg},
  journal= {arXiv preprint arXiv:2402.01917},
  year   = {2024}
}
R2 v1 2026-06-28T14:36:46.413Z