ritterkraft commited on
Commit
ea4f22f
·
verified ·
1 Parent(s): 5da89df

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -1
README.md CHANGED
@@ -1,4 +1,52 @@
1
- <img src="https://serve.thelabsource.com/u/VEshKD.png" alt="adi-qwen3.5-4b-glm5.2-general" width="800">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
 
3
  No cloud dependencies — wake detection through response generation runs entirely on local hardware.
4
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ library_name: openwakeword
6
+ tags:
7
+ - wake-word
8
+ - keyword-spotting
9
+ - openwakeword
10
+ - onnx
11
+ - tflite
12
+ - voice-assistant
13
+ - on-device
14
+ - adi
15
+ pipeline_tag: audio-classification
16
+ ---
17
+
18
+ <img src="https://huggingface.co/AdvancedDataIntelligence/hey-adi-wakeword/resolve/main/hey-adi-wakeword-banner.png" alt="hey-adi-wakeword" width="800">
19
+
20
+ # hey-adi-wakeword
21
+
22
+ Custom-trained **"Hey ADI"** wake word model for the [OpenWakeWord](https://github.com/dscripka/openWakeWord) framework. Built to trigger the **ADI Genesis** offline voice assistant pipeline at theLAB.
23
+
24
+ Wake phrase: **"hey addie"**
25
+
26
+ 📖 **Build writeup:** [How this wake word was trained](https://thelabsource.com/projects/custom-wake-word.php)
27
+
28
+ 🎥 **Demo video:**
29
+
30
+ [![Hey ADI Wake Word Demo](https://img.youtube.com/vi/BSkMgP5AfXw/maxresdefault.jpg)](https://www.youtube.com/watch?v=BSkMgP5AfXw)
31
+
32
+ ---
33
+
34
+ ## Files
35
+
36
+ | File | Format | Size | Runtime |
37
+ |------|--------|------|---------|
38
+ | `hey_addie.onnx` | ONNX | 206 kB | onnxruntime |
39
+ | `hey_addie.tflite` | LiteRT (TFLite) | 207 kB | tflite-runtime |
40
+
41
+ Both files are functionally equivalent — pick the runtime that fits your deployment target. ONNX for desktop/server, TFLite for edge/embedded.
42
+
43
+ ---
44
+
45
+ ## Pipeline
46
+
47
+ This wake word is the front door to a fully offline voice stack:
48
+
49
+ OpenWakeWord ("hey addie") → Parakeet STT → Ollama (advanced-data-intelligence:e4b) → OmniVoice TTS (adi_ref voice)
50
 
51
  No cloud dependencies — wake detection through response generation runs entirely on local hardware.
52