Add hey_beemo openWakeWord ONNX model

README.md

@@ -0,0 +1,45 @@
+---
+license: apache-2.0
+tags:
+  - openWakeWord
+  - wake-word
+  - audio
+  - onnx
+library_name: openwakeword
+pipeline_tag: audio-classification
+---
+
+# BMO openWakeWord model
+
+Custom [openWakeWord](https://github.com/dscripka/openWakeWord) model for the wake phrase **“Hey BMO”** (trained as `hey beemo`).
+
+## Files
+
+| File | Description |
+|------|-------------|
+| `hey_beemo.onnx` | Wake-word classifier head (ONNX) |
+
+Also requires the shared openWakeWord feature models at runtime:
+
+- `melspectrogram.onnx`
+- `embedding_model.onnx`
+
+(from [openWakeWord](https://github.com/dscripka/openWakeWord) / [openWakeWord-cpp](https://github.com/rhasspy/openWakeWord-cpp))
+
+## Usage with local-llm
+
+```json
+"model": {
+  "path": "../models/ww/hey_beemo.onnx"
+}
+```
+
+Or download from this repo:
+
+```bash
+hf download amrmantawi/bmo-openwakeword hey_beemo.onnx --local-dir models/ww
+```
+
+## Training
+
+Trained with the openWakeWord Google Colab automatic training notebook on synthetic speech for the phrase **hey beemo**.

hey_beemo.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df035b9be9357106b3398368b44dd4f65c4ee88f8cd20612e9b7d850c8b0c015
+size 206276