ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-05-17 07:52:56 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

docs : update README.md for whisper.objc app (#2569)

Browse Source
This commit is contained in:
Tomer Schlesinger 2025-05-13 06:03:50 +02:00 committed by GitHub
parent e41bc5c61a
commit 587ea01f55
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
examples/whisper.objc/README.md
View File

@ -26,10 +26,17 @@ If you don't want to convert a Core ML model, you can skip this step by creating
mkdir models/ggml-base.en-encoder.mlmodelc mkdir models/ggml-base.en-encoder.mlmodelc
``` ```
## Core ML ### Core ML support
1. Follow all the steps in the `Usage` section, including adding the ggml model file.
The ggml model file is required as the Core ML model is only used for the encoder. The
decoder which is in the ggml model is still required.
2. Follow the [`Core ML support` section of readme](../../README.md#core-ml-support) to convert the
model.
3. Add the Core ML model (`models/ggml-base.en-encoder.mlmodelc/`) to `whisper.swiftui.demo/Resources/models` **via Xcode**.
Follow the [`Core ML support` section of readme](../../README.md#core-ml-support) to convert the model. When the example starts running you should now see that it is using the Core ML model:
That is all the needs to be done to use the Core ML model in the app. The converted model is a ```console
resource in the project and will be used if it is available. Note that the Core ML model is only whisper_init_state: loading Core ML model from '/Library/Developer/CoreSimulator/Devices/25E8C27D-0253-4281-AF17-C3F2A4D1D8F4/data/Containers/Bundle/Application/3ADA7D59-7B9C-43B4-A7E1-A87183FC546A/whisper.swiftui.app/models/ggml-base.en-encoder.mlmodelc'
used for the encoder, the decoder which is in the ggml model is still required so both need to whisper_init_state: first run on a device may take a while ...
be available. whisper_init_state: Core ML model loaded
```