I'm super excited to share transcribe.cpp today. transcribe.cpp is a ggml based transcription library which supports all the latest transcription models. Every model published under the handy-computer HF org has been numerically validated and WER tested to match the reference implementation. It's accelerated everywhere. I'm the author and maintainer of Handy. This library grew from the pains of distributing a cross-platform speech-to-text application to many people. This is a v0.1.0 library which means that there are some rough edges which I cannot discover alone!

You get a fast and accurate inference engine with wide ranging model support. Support for 16 ASR Families (60+ models) with more coming. Acceleration via Vulkan, Metal, CUDA, and Tiny BLAS. Every model has been numerically verified and WER tested. Support for Streaming and Batch Transcription. More or less drop in whisper.cpp replacement. Maintainer supported bindings in 4 Languages: Python, Javascript/Typescript, Rust, Obj C/Swift.

transcribe.cpp is aimed squarely at making locally run ASR easier. We know that transcription can run extremely accurately on most devices, and there should be no need to send your voice to a cloud service. An RK3566 can run models via transcribe.cpp faster than real time on its anemic CPU. I am extremely thankful for all the folks who have supported this project. First and foremost is to Mozilla AI, their Bi R program, and Davide from Mozilla AI. Modal and Blacksmith also provided critical credits for testing and CI/CD.