Fact · Speech recognition
7.83percent average WER
On the Open ASR Leaderboard's English short-form tests, OpenAI Whisper Large v3 Turbo had an average word error rate of 7.83 percent, with an RTFx of 200.
Checked against its source on October 17, 2026
In the source's own words
“OpenAI Whisper Large v3 Turbo Yes 7.83 200”
Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation, Hugging Face and collaborators, arXiv, 2025, Table 3, short-form English.
Open the original- What it measures
- The turbo model is a faster, smaller variant of Whisper Large v3, and it ranks below the full Large v3 on this test.
- What it does not show
- Average over the leaderboard's English datasets. On other audio the order can change, which is why the paper reports several tracks.