Fact · Speech recognition
faster-whisper is a reimplementation of OpenAI's Whisper model that runs on the CTranslate2 inference engine.
Checked against its source on October 17, 2026
In the source's own words
“**faster-whisper** is a reimplementation of OpenAI's Whisper model using [CTranslate2](https://github.com/OpenNMT/CTranslate2/), which is a fast inference engine for Transformer models.”
faster-whisper: README (GitHub, SYSTRAN), SYSTRAN, GitHub (SYSTRAN/faster-whisper), 2026, Introduction.
Open the original- What it measures
- The opening paragraph of the faster-whisper README.
- What it does not show
- Describes the engine, not the speed. Speed claims are separate facts in the README and are measured on one hardware setup.