Fact · Speech recognition
10.5percent word error rate
A 2024 study that fine-tuned Whisper version 3 on about 68 hours of Northern Kurdish (Kurmanji) speech reached a word error rate of 10.5 percent on a specialized test set, using its best fine-tuning strategy.
Checked against its source on October 17, 2026
In the source's own words
“achieving a Word Error Rate (WER) of 10.5% and Character Error Rate (CER) of 5.7% with Whisper version 3”
End-to-End Transformer-based Automatic Speech Recognition for Northern Kurdish: A Pioneering Approach, Abdulhady Abas Abdullah et al., arXiv, 2024, Abstract.
Open the original- What it measures
- The authors compared vanilla, parameter-specific and additional-module fine-tuning on a Northern Kurdish corpus of about 68 hours of validated transcribed data. The 10.5 percent figure is for the additional-module strategy on a specialized test set.
- What it does not show
- One specialized test set and one corpus. The abstract does not give a figure for the untuned model, so this is not a measure of stock Whisper on everyday Kurmanji speech.