Whisper Norwegian and Scandinavian Dialect ASR Benchmark
OpenAI Whisper achieves 8 to 11% Word Error Rate on Standard Bokmål. On Northern Norwegian dialect, the same model exceeds 40% WER. Below is the full per-dialect benchmark across six Scandinavian varieties, three Whisper model sizes, with raw data downloadable as CSV.
By YPAI Research · Released · Updated
Results: Word Error Rate by Dialect
All values are 95% confidence intervals across multiple test runs. WER measured against normalized Bokmål reference transcriptions for Norwegian; standard orthography for Swedish and Danish.
| Dialect / Region | Language | Whisper large-v3 | Whisper medium | Whisper small | Hours | Speakers |
|---|---|---|---|---|---|---|
| Standard Bokmål (Oslo) | Norwegian | 8-11% | 13-17% | 19-24% | 7.8 | 34 |
| Western Norwegian (Bergen) | Norwegian | 25-31% | 38-44% | 51-58% | 5.6 | 22 |
| Trøndersk (Trondheim) | Norwegian | 28-34% | 41-49% | 54-61% | 4.9 | 21 |
| Northern Norwegian (Tromsø / Bodø) | Norwegian | 34-42% | 47-55% | 58-67% | 5.2 | 18 |
| Skånska (Malmö) | Swedish | 22-29% | 35-42% | 48-55% | 4.2 | 19 |
| Jutlandic Danish (Aarhus) | Danish | 26-38% | 40-51% | 55-63% | 5.1 | 24 |
Download CSV Read the full methodology & analysis
Methodology
Six Scandinavian dialect groups evaluated on a minimum of 4 hours of audio per group. Corpus size per dialect ranged from 4.2 to 7.8 hours. Speaker counts ranged from 18 to 34. Audio captured in controlled studio conditions and supplemented with in-cabin automotive test recordings under road noise at 55-72 dB SPL.
Whisper large-v3, medium, and small models tested with language forcing applied (--language no/sv/da). WER calculated against normalized Bokmål reference transcriptions for Norwegian dialect groups, with a secondary phonetic tier for dialect-specific forms.
Annotator agreement averaged 91.3% for Standard Bokmål, dropping to 78.6% for Northern Norwegian and 74.1% for Jutlandic Danish. Disagreements adjudicated by a third dialect-specialist annotator.
Test corpus is not publicly distributable due to GDPR Article 9 biometric data restrictions on Nordic speech recordings. Aggregate WER results, methodology, and dialect-specific phoneme analysis are released under CC-BY 4.0 for academic and commercial reference.
How to cite
YPAI Research (2026). Whisper Norwegian and Scandinavian Dialect ASR Benchmark.
YPAI. https://ypai.ai/research/asr-benchmark/
@misc{ypai2026whisperscandinavian,
author = {YPAI Research},
title = {Whisper Norwegian and Scandinavian Dialect ASR Benchmark},
year = {2026},
url = {https://ypai.ai/research/asr-benchmark/},
note = {CC-BY 4.0},
}
Need ASR that works on your target dialects?
YPAI builds dialect-native speech corpora for enterprise ASR: native annotators, deployment-realistic acoustic conditions, GDPR + EU AI Act compliant consent frameworks. Talk to us about your language coverage requirements.