Instructions to use TerminatorPower/whisperkit-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use TerminatorPower/whisperkit-coreml 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
metadata
pretty_name: WhisperKit CoreML Models
viewer: false
library_name: whisperkit
tags:
- whisper
- whisperkit
- coreml
- asr
- quantized
- automatic-speech-recognition
WhisperKit CoreML Models
Pre-compiled CoreML models for WhisperKit, an on-device speech recognition framework for Apple Silicon.
Usage
These models are drop-in replacements for the original argmaxinc/whisperkit-coreml repository. Use this repo by replacing the repo ID:
argmaxinc/whisperkit-coreml → TerminatorPower/whisperkit-coreml
Credits
All models were originally created and compiled by Argmax Inc. Full credit goes to the Argmax team for their work on WhisperKit and these CoreML model conversions.
- Original repo: argmaxinc/whisperkit-coreml
- WhisperKit: github.com/argmaxinc/WhisperKit
- WhisperKit paper (ICML 2025): icml.cc/virtual/2025/47854