Class-Notes-MCP

A modular Model Context Protocol (MCP) server for recording, transcribing, and generating class notes. This project utilizes whisper.cpp optimized for AMD hardware to deliver high-performance, local transcription.

Features

• MCP Integration: Designed to be integrated as a Model Context Protocol tool.
• AMD Hardware Optimization: Provides custom installation scripts and binaries tailored for AMD hardware (specifically targeting the A4-9125 and similar chipsets).
• Python Backend: Fast, modular Python-based architecture for processing audio and text.

Directory Structure

To maintain a clean and professional codebase, the project is organized as follows:

• mcp/: Core Model Context Protocol server implementation.
• config/: Configuration files (e.g., main_config.yaml, class_schedule.yaml).
• scripts/: Shell scripts for dependency installation, compiling, and fixing the whisper.cpp binaries for AMD.
• tests/: Python scripts for testing audio pipelines, benchmarking hardware, and verifying Whisper integration.
• Resources/: External assets and models.

Getting Started

Prerequisites

• Python 3.8+
• Required Python packages (see requirements.txt)
• (Optional but recommended) AMD hardware for optimal performance.

Installation

1. Clone the repository:

   git clone https://github.com/Charly-bite/Class-Notes-MCP.git
   cd Class-Notes-MCP

2. Set up the virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   pip install -r requirements.txt

3. Install AMD-Optimized Whisper (Linux/WSL): Execute the setup scripts located in the scripts/ directory:

   ./scripts/setup_amd_dependencies.sh
   ./scripts/install_whisper_amd_a4_9125.sh
   ./scripts/download_whisper_models_amd_a4_9125.sh

Running the Server

Execute the main server file:

python main_mcp.py

Contributing

Please see the CONTRIBUTING.md file for details on how to contribute to this project.

License

This project is licensed under the MIT License - see the LICENSE file for details.