From 21fb513ef1694e5ac58dce705bb254e7da81d095 Mon Sep 17 00:00:00 2001 From: Daniel Bevenius Date: Fri, 21 Mar 2025 09:52:53 +0100 Subject: [PATCH] examples : update whisper.objc README.md (#2916) This commit updates the hisper.objc README.md to reflect the changes of using the xcframework and the new build process. Since whisper.cpp is no longer compiled by the example project, instead the library from the xframework will be used, the build instructions have been removed. --- examples/whisper.objc/README.md | 42 ++++++++++----------------------- 1 file changed, 13 insertions(+), 29 deletions(-) diff --git a/examples/whisper.objc/README.md b/examples/whisper.objc/README.md index ece74aed..3fc7ad7d 100644 --- a/examples/whisper.objc/README.md +++ b/examples/whisper.objc/README.md @@ -11,39 +11,23 @@ https://user-images.githubusercontent.com/1991296/204126266-ce4177c6-6eca-4bd9-b ## Usage +This example uses the whisper.xcframework which needs to be built first using the following command: ```bash -git clone https://github.com/ggerganov/whisper.cpp -open whisper.cpp/examples/whisper.objc/whisper.objc.xcodeproj/ +./build_xcframework.sh +``` -# if you don't want to convert a Core ML model, you can skip this step by create dummy model +A model is also required to be downloaded and can be done using the following command: +```bash +./models/download-ggml-model.sh base.en +``` + +If you don't want to convert a Core ML model, you can skip this step by creating dummy model: +```bash mkdir models/ggml-base.en-encoder.mlmodelc ``` -Make sure to build the project in `Release`: - -image - -Also, don't forget to add the `-DGGML_USE_ACCELERATE` compiler flag for `ggml.c` in Build Phases. -This can significantly improve the performance of the transcription: - -image - ## Core ML -If you want to enable Core ML support, you can add the `-DWHISPER_USE_COREML -DWHISPER_COREML_ALLOW_FALLBACK` compiler flag for `whisper.cpp` in Build Phases: - -image - -Then follow the [`Core ML support` section of readme](../../README.md#core-ml-support) for convert the model. - -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. - -## Metal - -You can also enable Metal to make the inference run on the GPU of your device. This might or might not be more efficient -compared to Core ML depending on the model and device that you use. - -To enable Metal, just add `-DGGML_USE_METAL` instead off the `-DWHISPER_USE_COREML` flag and you are ready. -This will make both the Encoder and the Decoder run on the GPU. - -If you want to run the Encoder with Core ML and the Decoder with Metal then simply add both `-DWHISPER_USE_COREML -DGGML_USE_METAL` flags. That's all! +Follow the [`Core ML support` section of readme](../../README.md#core-ml-support) to convert the model. +That is all the needs to be done to use the Core ML model in the app. The converted model is a +resource in the project and will be used if it is available.