ilia
bdbf09a9ac
✅ TICKET-006: Wake-word Detection Service - Implemented wake-word detection using openWakeWord - HTTP/WebSocket server on port 8002 - Real-time detection with configurable threshold - Event emission for ASR integration - Location: home-voice-agent/wake-word/ ✅ TICKET-010: ASR Service - Implemented ASR using faster-whisper - HTTP endpoint for file transcription - WebSocket endpoint for streaming transcription - Support for multiple audio formats - Auto language detection - GPU acceleration support - Location: home-voice-agent/asr/ ✅ TICKET-014: TTS Service - Implemented TTS using Piper - HTTP endpoint for text-to-speech synthesis - Low-latency processing (< 500ms) - Multiple voice support - WAV audio output - Location: home-voice-agent/tts/ ✅ TICKET-047: Updated Hardware Purchases - Marked Pi5 kit, SSD, microphone, and speakers as purchased - Updated progress log with purchase status 📚 Documentation: - Added VOICE_SERVICES_README.md with complete testing guide - Each service includes README.md with usage instructions - All services ready for Pi5 deployment 🧪 Testing: - Created test files for each service - All imports validated - FastAPI apps created successfully - Code passes syntax validation 🚀 Ready for: - Pi5 deployment - End-to-end voice flow testing - Integration with MCP server Files Added: - wake-word/detector.py - wake-word/server.py - wake-word/requirements.txt - wake-word/README.md - wake-word/test_detector.py - asr/service.py - asr/server.py - asr/requirements.txt - asr/README.md - asr/test_service.py - tts/service.py - tts/server.py - tts/requirements.txt - tts/README.md - tts/test_service.py - VOICE_SERVICES_README.md Files Modified: - tickets/done/TICKET-047_hardware-purchases.md Files Moved: - tickets/backlog/TICKET-006_prototype-wake-word-node.md → tickets/done/ - tickets/backlog/TICKET-010_streaming-asr-service.md → tickets/done/ - tickets/backlog/TICKET-014_tts-service.md → tickets/done/
40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Configuration for 4080 LLM Server (Work Agent).
|
|
|
|
This server runs on a remote GPU VM or locally for testing.
|
|
Configuration is loaded from .env file in the project root.
|
|
"""
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
# Load .env file from project root (home-voice-agent/)
|
|
try:
|
|
from dotenv import load_dotenv
|
|
env_path = Path(__file__).parent.parent.parent / ".env"
|
|
load_dotenv(env_path)
|
|
except ImportError:
|
|
# python-dotenv not installed, use environment variables only
|
|
pass
|
|
|
|
# Ollama server endpoint
|
|
# Load from .env file or environment variable, default to localhost
|
|
OLLAMA_HOST = os.getenv("OLLAMA_HOST", "localhost")
|
|
OLLAMA_PORT = int(os.getenv("OLLAMA_PORT", "11434"))
|
|
OLLAMA_BASE_URL = f"http://{OLLAMA_HOST}:{OLLAMA_PORT}"
|
|
|
|
# Model configuration
|
|
# Load from .env file or environment variable, default to llama3:latest
|
|
MODEL_NAME = os.getenv("OLLAMA_MODEL", "llama3:latest")
|
|
MODEL_CONTEXT_WINDOW = 8192 # 8K tokens practical limit
|
|
MAX_CONCURRENT_REQUESTS = 2
|
|
|
|
# API endpoints
|
|
API_CHAT = f"{OLLAMA_BASE_URL}/api/chat"
|
|
API_GENERATE = f"{OLLAMA_BASE_URL}/api/generate"
|
|
API_TAGS = f"{OLLAMA_BASE_URL}/api/tags"
|
|
|
|
# Timeout settings
|
|
REQUEST_TIMEOUT = 300 # 5 minutes for large requests
|