Instructions to use argmaxinc/whisperkit-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use argmaxinc/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
whisperkit-coreml / openai_whisper-large-v3-v20240930_turbo /AudioEncoder.mlmodelc /analytics /coremldata.bin
Upload openai_whisper-large-v3-v20240930_turbo and openai_whisper-large-v3-v20240930_turbo_632MB, 4-bit compressed, outlier_decomp std 3, no qlora
736778e verified - Xet hash:
- ea42f3abd90221f3b77cbce1a6b98d4746c207dbd10b71848a0c3c986445a2ef
- Size of remote file:
- 243 Bytes
- SHA256:
- b58d36a7f4a729570b46b424ed8d847baefa07580e6cb9d47773ae738f8b845a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.