whisper (audio/whisper) Updated: 3 days, 6 hours ago Add to my watchlist

Port of OpenAI's Whisper model in C/C++

High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model

Version: 1.7.5 License: MIT

GitHub

Maintainers	exprez135
Categories	audio
Homepage	https://github.com/ggerganov/whisper.cpp
Platforms	darwin
Variants	base (Install base model) debug (Enable debug binaries) large (Install large model) medium (Install medium model) small (Install small model) tiny (Install tiny model) universal (Build for multiple architectures)

clang-17

cmake

No ports

Install this port's variants to include models, or download
your own and use the built-in `-m` feature.

Remember that whisper.cpp only functions on 16-bit WAV
files. You can use `ffmpeg -i input.mp3 -ar 16000
output.wav` to convert the file first.

3