| --- |
| license: apache-2.0 |
| tags: |
| - wake-word |
| - keyword-spotting |
| - openwakeword |
| - voice-assistant |
| language: |
| - en |
| pipeline_tag: audio-classification |
| library_name: openwakeword |
| --- |
| |
| # hey-orbis-wakeword |
|
|
| Custom wake word model for **"hey orbis"**, trained with [openWakeWord](https://github.com/dscripka/openWakeWord) and synthetic speech from Fish Audio S2 Pro. |
|
|
| ## Usage |
|
|
| ### With openWakeWord (Python) |
|
|
| ```python |
| from openwakeword.model import Model |
| |
| model = Model( |
| wakeword_models=["hey_orbis.onnx"], |
| inference_framework="onnx" |
| ) |
| |
| # Feed 80ms audio chunks (1280 samples at 16kHz, int16) |
| prediction = model.predict(audio_chunk) |
| if prediction["hey_orbis"] > 0.7: |
| print("Wake word detected!") |
| ``` |
|
|
| ### With Home Assistant |
|
|
| Copy `hey_orbis_float32.tflite` to your openWakeWord add-on's custom model directory. |
|
|
| ## Model Details |
|
|
| | Property | Value | |
| |----------|-------| |
| | Input | 16 frames × 96-dim Google speech embeddings (~1.3s window) | |
| | Output | Sigmoid probability [0, 1] | |
| | Framework | ONNX (primary), TFLite (Home Assistant) | |
| | Size | 199 KB (ONNX), 105 KB (TFLite fp16) | |
|
|
| ## Performance (v0) |
|
|
| Evaluated on synthetic test clips (Fish Audio S2 Pro) in streaming mode: |
|
|
| | Metric | @0.5 threshold | @0.7 threshold | |
| |--------|:--------------:|:--------------:| |
| | **Recall** | **92.4%** (924/1000) | **90.9%** (909/1000) | |
| | **FA rate** (adversarial) | 6.8% (27/400) | 5.5% (22/400) | |
|
|
| Adversarial negatives are phonetically similar phrases ("hey Morris", "hey Boris", etc.). Real-world FA rate against ambient speech will be lower. |
|
|
| ## Training Data |
|
|
| | Type | Source | Count | |
| |------|--------|------:| |
| | Positive | Fish Audio S2 Pro (5 voices, varied prosody) | ~7,000 clips | |
| | Adversarial negative | Fish Audio (similar-sounding phrases) | ~2,000 clips | |
| | Generic negative | ACAV100M pre-computed features | ~2,000 hours | |
| | Room impulse responses | MIT RIRs | 270 rooms | |
|
|
| ## Files |
|
|
| - `hey_orbis.onnx` — ONNX model for openWakeWord runtime |
| - `hey_orbis_float32.tflite` — TFLite for Home Assistant / edge |
| - `hey_orbis_float16.tflite` — TFLite half-precision (smaller) |
|
|
| ## Part of protoLabs |
|
|
| Built for [ORBIS](https://github.com/protoLabsAI/ORBIS), the open-source AI companion framework by [protoLabs](https://protolabs.studio). |
|
|
