ANEForge: Python for direct computation on the Apple Neural Engine
Paper • 2606.17090 • Published • 3
An unmodified duplicate of openai/whisper-tiny.en, tagged for use with
ANEForge so the weights load and run directly on the
Apple Neural Engine (no CoreML). Weights are byte-identical to the source; see the original repo for
the model details. Licensed apache-2.0 from the source.
# pip install "aneforge[models]"
import aneforge as af
asr = af.load_whisper("aneforge/whisper-tiny.en")
print(asr.transcribe(audio)) # audio: a 16 kHz mono float32 waveform -> transcript
ANEForge compiles the model's graph into a single ANE program and streams the weights from this repo
via huggingface_hub. See the docs and the paper.
Base model
openai/whisper-tiny.en