whisper.cpp High-Performance C/C++ Speech Recognition Engine
whisper.cpp is a lightweight, high-performance C/C++ port of OpenAI's Whisper automatic speech recognition model. It runs on CPU and GPU across all major platforms with zero dependencies and zero runtime memory allocations.
Installation
Use the upstream install or setup path that matches your environment:
- git clone https://github.com/ggml-org/whisper.cpp.git
- cmake -B build
- cmake --build build -j --config Release
Requirements and caveats from upstream:
Basic usage or getting-started notes:
As an example, here is a video of running the model on an iPhone 13 device - fully offline, on-device: whisper.objc
First clone the repository:
bash
Extracted from upstream docs: https://raw.githubusercontent.com/ggml-org/whisper.cpp/HEAD/README.md