“Hi Emma” wake word model
Open-source openWakeWord model for the wake word “Hi Emma”, trained on openwakeword.com from synthetic speech (not recorded). It runs fully on-device with the openWakeWord runtime: Home Assistant (openWakeWord add-on), Rhasspy, OpenVoiceOS and any Python project.
Model facts
- Wake word
- “Hi Emma”
- Trained
- 2026-02-09 · pipeline V1
- Network
- 64 × 3 layers, 75,000 training steps
- Recall, with background noise and room reverb
- 26.4%
- False activations on the benchmark set
- 11.25 per hour
- Files
- ONNX (405 KB)
- Downloads
- 6
Recall is measured on 500 synthetic test utterances; false activations on about 10 hours of near-miss phrases, noise and read speech, one activation per frame at or above the threshold with a 2-second refractory period.
Download
Sign in on this page to download the model as ONNX (405 KB). Downloads are free; models are licensed for personal and non-commercial use by default (commercial license).
This model ships as ONNX only, which the openWakeWord Python runtime, Rhasspy and OpenVoiceOS load directly; the Home Assistant add-on needs a TFLite file, which newer trainings provide.
Use it in Python
from openwakeword.model import Model
model = Model(wakeword_models=["Hi_Emma_20260209_111337.onnx"], inference_framework="onnx")
# feed 16 kHz mono int16 audio in 1280-sample frames; a score above the threshold is an activation
scores = model.predict(frame)Similar wake words in the library
- “Hey Nova” — 90.4% recall
- “Pico” — 44.6% recall
- “hey bro” — 81.4% recall
- “Hey Jarvis” — 69.8% recall
- “Jarvis” — 46.2% recall
- “Jarvis” — 36.8% recall
Custom wake words are trained in the Training Center; the library lists every public model with the same measurements.