Minimal Obj-C application for automatic offline speech recognition. The inference runs locally, on-device.
whisper-iphone-13-mini-2.mp4
Real-time transcription demo:
whisper-iphone-13-mini-3.mp4
git clone https://github.com/ggerganov/whisper.cpp
open whisper.cpp/examples/whisper.objc/whisper.objc.xcodeproj/Make sure to build the project in Release:
Also, don't forget to add the -DGGML_USE_ACCELERATE compiler flag in Build Phases.
This can significantly improve the performance of the transcription:
In this project, it also added -O3 -DNDEBUG to Other C Flags, but adding flags to app proj is not ideal in real world (applies to all C/C++ files), consider splitting xcodeproj in workspace in your own project.