Preprint
Evaluating OpenAI's Whisper ASR: Performance analysis across diverse accents and speaker traits
Calbert Graham and Nathan Roll, Cambridge Open Engage (preprint); published in JASA Express Letters, 2024, 2024 · DOI 10.33774/coe-2023-8fcj1
Read the originalRead on October 17, 2026
- What it is
- A study that tested OpenAI's Whisper speech model on native and non-native English accents and on read and conversational speech, then linked error rates to speaker traits. The preprint page lists it as published in JASA Express Letters in February 2024.
- How much weight it carries
- The published version appeared in a peer-reviewed acoustics journal. We read only the preprint abstract, so the accent-by-accent figures are not in this library. The study tests one open model, not the dictation engines built into Apple or Microsoft systems.
Facts taken from this source
- In a 2024 analysis of OpenAI's Whisper speech model, the authors found better performance on North American English accents than on British and Irish English accents.
“The findings indicate better performance on North American vs British and Irish English accents” (Abstract)