This repository provides GGUF quantized versions of OpenAI's Whisper-medium model for use with transcribe.cpp and other GGUF-compatible runtimes. It supports transcription in 99 languages and can run efficiently on consumer hardware without requiring cloud services.
In the Speech to text space, Whisper Medium takes a focused approach. It focuses on running accurate multilingual speech recognition locally with reduced memory requirements. It is built as an open-source project for developers building offline transcription tools. The project is open source (MIT). It runs on the web and API.
Behind Whisper Medium is Handy Computer, and it first shipped in 2026. Development happens publicly on GitHub with 1.4k stars and 419 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 5 similar projects. Among its 4 catalogued features are speech-to-Text, Multilingual Transcription, and GGUF Quantization.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do