Fact · Languages and accents
36.2BLEU points
On the CoVoST 2 test of speech translated into English, zero-shot Whisper scored 36.2 BLEU for high-resource languages.
Checked against its source on October 17, 2026
In the source's own words
“Maestro 38.2 31.3 18.4 25.2 Zero-Shot Whisper 36.2 32.6 25.2 29.1”
Robust Speech Recognition via Large-Scale Weak Supervision (full text), Alec Radford et al., OpenAI (arXiv), 2022, Table 4, X to English speech translation.
Open the original (DOI 10.48550/arXiv.2212.04356)- What it measures
- The table groups languages into high, mid and low resource tiers. Zero-shot means Whisper was not trained on the CoVoST 2 training data for this test.
- What it does not show
- In the high tier, the older Maestro system scored higher, so Whisper trails supervised systems for well-resourced languages. The result covers read speech and BLEU scores only.