xenova / whisper-web

ML-powered speech recognition directly in your browser
https://hf.co/spaces/Xenova/whisper-web
MIT License
1.29k stars 152 forks source link
javascript transformers whisper

Whisper Web

ML-powered speech recognition directly in your browser! Built with 🤗 Transformers.js.

Check out the demo site here.

[!IMPORTANT]
Experimental WebGPU support has been added to this branch (demo), if you'd like to run with GPU acceleration!

https://github.com/xenova/whisper-web/assets/26504141/fb170d84-9678-41b5-9248-a112ecc74c27

Running locally

  1. Clone the repo and install dependencies:

    git clone https://github.com/xenova/whisper-web.git
    cd whisper-web
    npm install
  2. Run the development server:

    npm run dev

    Firefox users need to change the dom.workers.modules.enabled setting in about:config to true to enable Web Workers. Check out this issue for more details.

  3. Open the link (e.g., http://localhost:5173/) in your browser.