Wake word sensitivity (#207)

## Summary
- Introduces configurable wake word and stop word sensitivity
- Adds UI-controllable thresholds for wake word detection
- Refactors wake word loading and handling logic
- Improves audio preprocessing and runtime behavior

## Key Features
- Per-wake-word sensitivity configuration (Wake Word 1 & 2)
- Configurable stop word sensitivity
- Fine-grained numeric control (0.0 – 1.0, step 0.001)
- Sensitivity values exposed as Number Entities for Home Assistant
- Persistent storage of user-defined sensitivity values

## Wake Word Handling
- Support for model-specific default thresholds (`probability_cutoff`)
- Automatic fallback to defaults if no user value is set
- Separate thresholds for:
  - Wake Word 1
  - Wake Word 2
  - Stop Word
- Unified handling for MicroWakeWord and OpenWakeWord models

## UI / API Integration
- Adds new Home Assistant entities:
  - `WakeWord1SensitivityNumberEntity`
  - `WakeWord2SensitivityNumberEntity`
  - `StopWordSensitivityNumberEntity`
- Entities support:
  - Live updates
  - Persistence via preferences
  - Synchronization with runtime state
- Pushes updated values to Home Assistant on startup

## Refactoring
- Extracted wake word logic into `wake_word.py`
  - Model discovery
  - Model loading
  - Stop word handling
- Simplified `__main__.py` by delegating wake word responsibilities
- Improved separation between configuration and runtime state

## Additional Changes
- Improved debug logging across initialization and runtime

## Impact
- Enables fine-tuning of wake word detection accuracy
- Reduces false positives and missed triggers
- Improves usability via UI-based configuration
- Provides better flexibility across different environments and microphones

docs/audio_options.md

@@ -1,4 +1,4 @@
-# Audio Options: Gain and Noise Suppression
+# Audio Options: Gain, Noise Suppression, and Wake Word Sensitivity
 
 ## What do Gain and Noise Suppression do
 
@@ -47,3 +47,27 @@ LVA exposes two slider entities to change these gain and noise suppression from
 💡 **Note:**  Setting the flag and ENV values to 0 turns them off and are not used.
 
 💡 **Note:**  Keep in mind that when the flags are set they will overwrite the previous value in the preferences file and also they will be overridden if the value is changed in Home Assistant(Also applies to the ENV file but the ENV file will always overwrite the last value on startup).
+
+
+## Wake Word Sensitivity
+ 
+LVA exposes three numeric controls in the Home Assistant device page for fine-grained sensitivity tuning. These let you dial in the exact probability threshold that best matches your microphone quality, room acoustics, and false-activation tolerance.
+ 
+| Entity | Description | Default |
+|--------|-------------|---------|
+| **Wake Word 1 Sensitivity** | Probability cutoff for the primary wake word | From model manifest |
+| **Wake Word 2 Sensitivity** | Probability cutoff for the secondary wake word (if active) | From model manifest |
+| **Stop Word Sensitivity** | Probability cutoff for the stop word | From model manifest |
+ 
+Values range from `0.0` to `1.0`:
+ 
+- **Higher value** (e.g. `0.95`) → more selective, fewer false activations, may miss quieter or accented speech
+- **Lower value** (e.g. `0.50`) → more responsive, but more likely to trigger on similar-sounding words
+The defaults are read directly from each model's `.json` manifest file (the `probability_cutoff` field), so bundled models like `okay_nabu` (0.85), `hey_jarvis` (0.97), and custom downloaded models all start at their author-tested baseline. Changes made in the Home Assistant UI are persisted in `preferences.json` and survive restarts.
+ 
+**Tuning guide:**
+ 
+- If the wake word **rarely activates** (misses your voice): lower the value slightly, e.g. by `0.05` steps
+- If the wake word **activates too often** (false triggers from TV, music, or similar words): raise the value slightly
+- Start from the model's default and make small adjustments — a change of `0.05–0.10` is usually enough to notice a difference
+- Far-field microphones with noise cancellation (e.g. ReSpeaker, Satellite1) generally work well at the default values; basic USB microphones may need a lower threshold