Commit Graph

3 Commits

Author SHA1 Message Date
ce2b25a599 Migration Gitea - sauvegarde locale 2025-12-04 18:58 2025-12-04 18:58:32 +08:00
a712988584 feat: Phase 7 STT - Complete implementation with 4 engines
Implemented complete STT (Speech-to-Text) system with 4 engines:

1. **PocketSphinxEngine** (new)
   - Lightweight keyword spotting
   - Perfect for passive wake word detection
   - ~10MB model, very low CPU/RAM usage
   - Keywords: "celuna", "hey celuna", etc.

2. **VoskSTTEngine** (existing)
   - Balanced local STT for full transcription
   - 50MB models, good accuracy
   - Already working

3. **WhisperCppEngine** (new)
   - High-quality offline STT using whisper.cpp
   - 75MB-2.9GB models depending on quality
   - Excellent accuracy, runs entirely local

4. **WhisperAPIEngine** (existing)
   - Cloud STT via OpenAI Whisper API
   - Best accuracy, requires internet + API key
   - Already working

Features:
- Full JSON configuration via config/voice.json
- Auto-selection mode tries engines in order
- Dual mode support (passive + active)
- Fallback chain for reliability
- All engines use ISTTEngine interface

Updated:
- STTEngineFactory: Added support for all 4 engines
- CMakeLists.txt: Added new source files
- docs/STT_CONFIGURATION.md: Complete config guide

Config example (voice.json):
{
  "passive_mode": { "engine": "pocketsphinx" },
  "active_mode": { "engine": "vosk", "fallback": "whisper-api" }
}

Architecture: ISTTService → STTEngineFactory → 4 engines
Build:  Compiles successfully
Status: Phase 7 complete, ready for testing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-29 17:27:47 +08:00
3c588a9f90 feat: Phase 6 - Interactive mode validated with TTS
 Validated AISSIA interactive mode with real conversations
- Claude Sonnet 4 agentic loops working perfectly
- espeak-ng TTS integration functional (French voice)
- 7 modules + 4 services + 18 tools operational
- Tested conversation with tool usage (get_current_time)
- 4298 tokens, 2 agentic iterations, TTS output

📝 Documentation:
- Added docs/PHASE6_VALIDATION.md (complete validation report)
- Updated README.md roadmap (Phase 6 complete)

🎉 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-29 07:45:21 +08:00