mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-04-27 14:29:43 +00:00
854c0518bc
This commit clarifies the usage of the Core ML encoder model in the whisper.obj and whisper.swiftui examples. Refs: https://github.com/ggerganov/whisper.cpp/issues/2783
36 lines
1.2 KiB
Markdown
36 lines
1.2 KiB
Markdown
# whisper.objc
|
|
|
|
Minimal Obj-C application for automatic offline speech recognition.
|
|
The inference runs locally, on-device.
|
|
|
|
https://user-images.githubusercontent.com/1991296/197385372-962a6dea-bca1-4d50-bf96-1d8c27b98c81.mp4
|
|
|
|
Real-time transcription demo:
|
|
|
|
https://user-images.githubusercontent.com/1991296/204126266-ce4177c6-6eca-4bd9-bca8-0e46d9da2364.mp4
|
|
|
|
## Usage
|
|
|
|
This example uses the whisper.xcframework which needs to be built first using the following command:
|
|
```bash
|
|
./build-xcframework.sh
|
|
```
|
|
|
|
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
|
|
```
|
|
|
|
## Core ML
|
|
|
|
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. Note that the Core ML model is only
|
|
used for the encoder, the decoder which is in the ggml model is still required so both need to
|
|
be available.
|