sebastian-software/whisper-coreml-models

Whisper CoreML Models

Pre-converted CoreML encoder models for whisper.cpp, optimized for Apple Neural Engine (ANE) acceleration.

Models

Model	Size	Description
ggml-large-v3-turbo-encoder.mlmodelc	~1.3 GB	Whisper large-v3-turbo encoder, ANE-optimized

Usage

These models are used by whisper-coreml for Node.js speech recognition with Neural Engine acceleration.

npm install whisper-coreml
npx whisper-coreml download

Conversion

Models were converted using whisper.cpp's conversion tools:

python3 models/convert-whisper-to-coreml.py --model large-v3-turbo --encoder-only True --optimize-ane True
xcrun coremlc compile models/coreml-encoder-large-v3-turbo.mlpackage models/

Performance

On Apple M1 Ultra:

• 14x real-time transcription speed
• 1 hour of audio in ~4.5 minutes

License

MIT - Same as whisper.cpp

Credits

• OpenAI Whisper
• whisper.cpp
• Apple Neural Engine Transformers