Fact · Speech recognition
125seconds
In the same CPU benchmark, whisper.cpp took 2 minutes 5 seconds (125 seconds) with the small model in fp32 precision.
Checked against its source on October 17, 2026
In the source's own words
“| whisper.cpp | fp32 | 5 | 2m05s | 1049MB |”
faster-whisper: README (GitHub, SYSTRAN), SYSTRAN, GitHub (SYSTRAN/faster-whisper), 2026, Small model on CPU table.
Open the original- What it measures
- The row is part of the same CPU benchmark as the openai/whisper row, with 8 threads on an Intel Core i7-12700K.
- What it does not show
- One run. The row reports about 1,049 MB of RAM, which is the lowest memory figure of the three CPU rows.