Fact · Languages and accents
OpenAI's Whisper README says the model's performance varies widely depending on the language, and it publishes a breakdown by language for its two largest models.
Checked against its source on October 17, 2026
In the source's own words
“Whisper's performance varies widely depending on the language.”
openai/whisper: README (raw text), OpenAI, GitHub (openai/whisper), 2026, Available models and languages.
Open the original- What it measures
- The README links a per-language chart of word and character error rates on the Common Voice 15 and FLEURS benchmarks for large-v3 and large-v2.
- What it does not show
- The README gives the chart as an image, so the numbers are read from the chart rather than the text.