Fact · Speech recognition
The first run of whisper.cpp on a device with Core ML is slow, because the Neural Engine service compiles the model to a device-specific format.
Checked against its source on October 17, 2026
In the source's own words
“The first run on a device is slow, since the ANE service compiles the Core ML model to some device-specific format.”
whisper.cpp README, Georgi Gerganov, GitHub, 2026, Core ML support.
Open the original- What it measures
- The README says later runs are faster. The compiled form is specific to the device, so each Mac compiles the model once.
- What it does not show
- The README gives no figure for how long the first run takes.