Search results

whisper.cpp

github.com

A C/C++ port of OpenAI's Whisper automatic speech recognition model, providing high-performance inference without dependencies. It supports CPU-only inference and GPU backends, and runs on platforms including macOS, iOS, Android, Linux, Windows, WebAssembly and Raspberry Pi. The whisper-cli example currently runs only with 16-bit WAV files.

whisper.cpp offers a minimal example that runs in the browser, allowing a ggml model file to be loaded and an audio file or microphone recording to be transcribed. The example notes that computation is quite heavy and may take a few seconds. The browser must support WASM SIMD instructions.