ggerganov / whisper.cpp

whisper.cpp is a high-performance, lightweight C++ port of OpenAI's Whisper speech-to-text model, originally developed by Georgi Gerganov. It enables developers to run accurate, offline speech transcription directly on everyday hardware, including standard CPUs, without relying on cloud APIs or massive GPU infrastructure. Built with zero dependencies, it allows for seamless integration into various operating systems and platforms such as Windows, macOS, Linux, iOS, and Android. By leveraging low-bit quantization and specialized Apple Silicon optimizations, the library drastically reduces memory usage and inference latency. This project is a foundational game-changer for building privacy-focused applications, custom voice interfaces, and local transcription tools, making cutting-edge AI speech recognition universally accessible for edge computing.