Open-source multi-room music system for Pi and other SBCs
Supports various audio formats and streaming services
User-friendly web interface for configuration and control
Customizable with various themes and plugins
Can be controlled via voice commands using Amazon Alexa or Google Home
- Shows how an individual can use Python for speech recognition (SR), Push-to-- Talk (PTT) systems, and large action models to create their own AI assistant.
- Describes the process of creating a "la Rabbit prototype" with Python code on Raspberry Pi hardware.
- Emphasizes how these components can be combined for various tasks using different APIs like OpenAI or LLaMA (Large Language Model from Meta).
Sudo raspi-config -> Advanced Options -> Bootloader Version -> E1 Latest -> Reset Boot Rom to Defaults -> No
Resource-efficient LLMs and Multimodal Models
A useful survey of resource-efficient LLMs and multimodal foundations models.
Provides a comprehensive analysis and insights into ML efficiency research, including architectures, algorithms, and practical system designs and implementations.