This is a GGUF quantized version of the Whisper large v3 turbo model optimized for local inference using transcribe.cpp. It supports transcription and translation across 100 languages. The repository provides multiple quantization levels (F16, Q4, Q5, Q6, Q8) for different performance and accuracy tradeoffs on CPU and GPU hardware. It is intended for developers building offline speech recognition applications.
Whisper Large V3 Turbo sits in PulseGate's Speech to text category. It focuses on running large Whisper speech recognition models efficiently on local hardware with reduced memory usage. It is built as an open-source project for developers. The project is open source (MIT). Whisper Large V3 Turbo is available on the web and the command line.
Behind Whisper Large V3 Turbo is handy-computer, and it first shipped in 2026. Development happens publicly on GitHub with 852 stars and 423 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 9 similar projects. Key capabilities include speech-to-Text, Quantized GGUF, and Multilingual ASR.
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