Fact · Speech recognition
418seconds
In the faster-whisper CPU benchmark, openai/whisper took 6 minutes 58 seconds (418 seconds) with the small model in fp32 precision.
Checked against its source on October 17, 2026
In the source's own words
“| openai/whisper | fp32 | 5 | 6m58s | 2335MB |”
faster-whisper: README (GitHub, SYSTRAN), SYSTRAN, GitHub (SYSTRAN/faster-whisper), 2026, Small model on CPU table.
Open the original- What it measures
- The README says the CPU runs used 8 threads on an Intel Core i7-12700K. The row uses fp32 precision and beam size 5.
- What it does not show
- One run on one CPU. The RAM figure for this row is 2335 MB.