Custom wake-word models for the
REX voice assistant.
REX 0.3.2+ downloads this model automatically when wake-word gating is enabled.
1from openwakeword.model import Model
2oww = Model(wakeword_models=["hey_rex.onnx"], inference_framework="onnx")
3score = oww.predict(audio_int16_chunk_1280_samples)["hey_rex"]
Audio format: 16 kHz mono int16, fed in chunks of 1280 samples (80 ms).
Default detection threshold: 0.5 (raise to ~0.7 to reduce false fires).
MIT, matching the REX project. Voice samples used in training were collected
with explicit consent from contributors for inclusion in this model and its
distribution (including any commercial distribution, though none is intended).
