Fact · Languages and accents
6.7percent word error rate
On the FLEURS read-speech benchmark, Whisper large-v2 had a word error rate of 6.7 percent in Dutch.
Checked against its source on October 17, 2026
In the source's own words
“Whisper large-v2 6.7 75.3 102.4 5.4 93.7 4.3 14.4 5.6”
Robust Speech Recognition via Large-Scale Weak Supervision (full text), Alec Radford et al., OpenAI (arXiv), 2022, Appendix D.2.4, FLEURS transcription table, Dutch column.
Open the original (DOI 10.48550/arXiv.2212.04356)- What it measures
- Table D.2.4 lists word error rates (%) on FLEURS. The header for this block reads Dutch, Occitan, Punjabi, Polish, Pashto, Portuguese, Romanian, Russian, so the first figure is Dutch.
- What it does not show
- FLEURS is read Wikipedia sentences, recorded in quiet rooms. It is a benchmark, not a measure of dictation at your desk, and it uses the paper's own text normalization.