ML-powered speech recognition directly in your browser! Built with 🤗 Transformers.js.
Check out the demo site here.
whisper-webgpu.mp4
-
Clone the repo and install dependencies:
git clone https://github.com/xenova/whisper-web.git cd whisper-web npm install
-
Run the development server:
npm run dev
Firefox users need to change the
dom.workers.modules.enabled
setting inabout:config
totrue
to enable Web Workers. Check out this issue for more details. -
Open the link (e.g., http://localhost:5173/) in your browser.
-
build the project
npm run hf-build
-
push the project to Hugging Face Spaces
cd dist git commit # if you have made any changes git push # (you need to configure the ssh keys before pushing to the repo)