Fact · Speech recognition
The Whisper paper concludes that its English speech recognition is not perfect but very close to human-level accuracy.
Checked against its source on October 17, 2026
In the source's own words
“English ASR performance is not perfect but very close to human-level accuracy”
Robust Speech Recognition via Large-Scale Weak Supervision (full text), Alec Radford et al., OpenAI (arXiv), 2022, Section 3.3, English Speech Recognition.
Open the original (DOI 10.48550/arXiv.2212.04356)- What it measures
- The authors compare Whisper with human transcription across several English test sets, which vary in difficulty.
- What it does not show
- A claim about the authors' own comparison on their test sets. It is not a claim that Whisper matches a professional on every recording.