“hey_mee_meer” wake word model

Open-source openWakeWord model for the wake word “hey_mee_meer”, trained on openwakeword.com from synthetic speech (English (US), German). It runs fully on-device with the openWakeWord runtime: Home Assistant (openWakeWord add-on), Rhasspy, OpenVoiceOS and any Python project.

Model facts

Wake word
“hey_mee_meer”
Language of the training voices
English (US), German
Trained
2026-06-29 · pipeline V3
Network
64 × 3 layers, 115,000 training steps
Recall, with background noise and room reverb
48.0%
False activations on the benchmark set
8.97 per hour at threshold 0.5
Files
ONNX (812 KB), TFLite (825 KB)
Downloads
2

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 (812 KB) or TFLite (825 KB). Downloads are free; models are licensed for personal and non-commercial use by default (commercial license).

Use it in Home Assistant

  1. Download the TFLite file and copy it to the /share/openwakeword folder of your Home Assistant server.
  2. Install the openWakeWord add-on and restart it so it picks up the new file.
  3. In Settings → Voice assistants, open your assistant and choose “hey_mee_meer” as the wake word.
  4. Say “hey_mee_meer” to your satellite or to the Home Assistant Voice Preview Edition.

Use it in Python

from openwakeword.model import Model

model = Model(wakeword_models=["hey_mee_meer_20260629_213434.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

Custom wake words are trained in the Training Center; the library lists every public model with the same measurements.