Instructions to use aoiandroid/whisperkit-coreml-macos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use aoiandroid/whisperkit-coreml-macos with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- Notebooks
- Google Colab
- Kaggle
WhisperKit Core ML (macos)
Platform-compiled WhisperKit bundles for TranslateBlue.
- Source weights:
argmaxinc/whisperkit-coreml - This repo: macos compiled
.mlmodelc(same variant folder names as Argmax) - Sibling:
aoiandroid/whisperkit-coreml-ios
Folder layout matches WhisperKit (AudioEncoder.mlmodelc, TextDecoder.mlmodelc, MelSpectrogram.mlmodelc, optional TextDecoderContextPrefill.mlmodelc).
ANE specialization cache is still device-local (Apple). These bundles avoid iOS rejecting a macOS coremlcompiler tree with “Compile the model…”.
- Downloads last month
- -