Fact · Speech recognition
7times the speed of large
The base Whisper model runs at about 7 times the relative speed of the large model.
Checked against its source on October 17, 2026
In the source's own words
“| base | 74 M | `base.en` | `base` | ~1 GB | ~7x |”
openai/whisper: README (raw text), OpenAI, GitHub (openai/whisper), 2026, Available models and languages table.
Open the original- What it measures
- The README measured relative speed by transcribing English speech on an A100 GPU.
- What it does not show
- Speed depends on language, speaking rate and hardware, and the README says so.