Switch wake word from Porcupine to openwakeword + training pipeline

- Add training/ pipeline (step_1..step_5) and own-samples flow
- record_wav.py with single-shot and long-record modes, RMS-based silence filter
- remove_silent.py to drop silent samples and renumber
- modes.py: openwakeword inference with reset() and quiet predictions; commented Lusya block for later
- stt.py: drop local faster-whisper fallback, Groq-only
- config.py: remove unused STT_PROVIDER/WHISPER_*
- llm.py: replace __import__("os") hack with proper import
- tts.py: remove debug traceback in play_error_sound
- requirements.txt: add openwakeword/sounddevice/scipy, drop faster-whisper
- deploy/setup.sh: validate ELEVENLABS_API_KEY and WAKE_WORD_COSMO presence
- README.md, CLAUDE.md, project_roadmap memory updated to reflect new architecture

requirements.txt

@@ -1,9 +1,17 @@
-faster-whisper
-pyaudio
 requests
 python-dotenv
 numpy
+
+# Audio I/O
+pyaudio
+sounddevice
+scipy
+
+# STT через облако
 groq
+
+# TTS
 elevenlabs
-# Раскомментировать когда будет Pi + Porcupine:
-# pvporcupine
+
+# Wake word
+openwakeword