- Extend upstream hermes-agent image
- Add libportaudio2 for audio capture
- Install sounddevice, numpy, faster-whisper via uv
- Add health check for voice dependencies
- Include Dockerfile.full for future complete rebuild from source
- Dockerfile: add libportaudio2 system library for audio capture
- Dockerfile: install sounddevice, numpy, faster-whisper for local STT
- compose.yml: add ROCm environment variables for AMD GPU support
Enables local faster-whisper STT with GPU acceleration via ROCm.