# Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges

arXiv: https://arxiv.org/abs/2402.01917 · HTML: https://mlsanity.com/paper/2402.01917/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 6 of 6)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model](https://mlsanity.com/paper/2104.09617/) (2021)
- [Boosting Norwegian Automatic Speech Recognition](https://mlsanity.com/paper/2307.01672/) (2023)

## Built on by (most cited first, 4 of 4)

- [A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data](https://mlsanity.com/paper/2506.11130/) (2025)
- [Whispering in Amharic: Fine-tuning Whisper for Low-resource Language](https://mlsanity.com/paper/2503.18485/) (2025)
- [Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation](https://mlsanity.com/paper/2503.03186/) (2025)
- [Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition](https://mlsanity.com/paper/2505.17538/) (2025)

## Abstract (arXiv)

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 Bokmaal 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.