Whisper ANE encoders (ANEForge)
Whisper audio encoders compiled for the Apple Neural Engine (ANE) with ANEForge, for use with the whisper-aneforge backend for whisper.cpp.
Available bundles
whisper-small-ane/
Each bundle is self-contained in its own directory. The ANE program is
compiled on-device at load (about 0.6 s) from model.mil + weights.bin;
no prebuilt binaries are shipped.
Usage
Download a bundle (e.g. whisper-small-ane):
hf download danbev/whisper-ane --include 'whisper-small-ane/*' --local-dir models
Build whisper.cpp with the ANEForge backend (see the whisper-aneforge README), then run, pointing the backend at the bundle and the ANEForge dispatch dylib:
ANEFORGE_DYLIB=$(python -c "import aneforge,os;print(os.path.join(os.path.dirname(aneforge.__file__),'_lib','libane_e5rt_dispatch.dylib'))") \
ANEFORGE_ENCODER=models/whisper-small-ane \
./build/bin/whisper-cli -m models/ggml-small.bin -f samples/jfk.wav
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support