Library / SDK
Inference & Serving
whisper.cpp
1Fast 2portable 3Whisper 4transcription 5in 6C++
the six Ws · specification
W1
Who
Created by Georgi Gerganov and maintained by the ggml-org community.
W2
What
whisper.cpp is a C and C++ port of OpenAI's Whisper automatic speech recognition model optimized for CPU and edge devices.
W3
Where
Hosted on GitHub at ggml-org/whisper.cpp, migrated from the original ggerganov/whisper.cpp repository.
W4
When
Released in 2022 shortly after OpenAI open sourced Whisper.
W5
Why
It enables fast, dependency free speech transcription on laptops, phones and embedded devices without a Python runtime or GPU.
W6
With
Built on the GGML tensor library with optional CUDA, Metal and Core ML backends.
W7
Watch
MIT licensed, open source, maintained by Georgi Gerganov and the ggml-org community, roughly 53k GitHub stars.