FL33TW00D/whisper-turbo
A fast, cross-platform WebGPU implementation of OpenAI's Whisper speech-to-text model for browser and Electron environments.
Not currently ranked — collecting fresh signals.
star history
Whisper Turbo provides client-side inference of OpenAI’s Whisper speech recognition model using WebGPU for GPU acceleration. It is built on a Rust library called Ratchet and runs entirely in the browser or Electron applications without server dependencies. The implementation targets Windows and MacOS on Chromium-based browsers, enabling real-time speech-to-text transcription directly on the client device.
Frequently asked
- What is FL33TW00D/whisper-turbo?
- A fast, cross-platform WebGPU implementation of OpenAI's Whisper speech-to-text model for browser and Electron environments.
- Is whisper-turbo open source?
- Yes — FL33TW00D/whisper-turbo is open source, released under the Apache-2.0 license.
- What language is whisper-turbo written in?
- FL33TW00D/whisper-turbo is primarily written in TypeScript.
- How popular is whisper-turbo?
- FL33TW00D/whisper-turbo has 1.8k stars on GitHub.
- Where can I find whisper-turbo?
- FL33TW00D/whisper-turbo is on GitHub at https://github.com/FL33TW00D/whisper-turbo.