This can significantly improve the performance of the transcription:
<img width="1072" alt="image" src="https://user-images.githubusercontent.com/1991296/208511239-8d7cdbd1-aa48-41b5-becd-ca288d53cc07.png">
+
+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.
2. Add the model to "whisper.swiftui.demo/Resources/models" via Xcode.
3. Select a sample audio file (for example, [jfk.wav](https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav)).
4. Add the model to "whisper.swiftui.demo/Resources/samples" via Xcode.
-5. Select the "release" build configuration under "Run", then deploy and run to your device.
+5. Select the "Release" [^2] build configuration under "Run", then deploy and run to your device.
[^1]: I recommend the tiny, base or small models for running on an iOS device.
+[^2]: The `Release` build can boost performance of 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.
