Disclaimer: The code is derived from the original Whisper web project. Huge shoutout to @xenova for an amazing use-case of Whisper model!
ML-powered speech recognition directly in your browser! Built with 🤗 Transformers.js. Check out the demo site here. https://github.com/xenova/whisper-web/assets/26504141/5d6ed3d9-5f99-4d89-8e38-9d4fc8d5baaf
- Update the .env file with url to backend (make sure the URL is pointing to envoy proxy and not gRPC service directly).
- Make sure to first generate the protoc files for frontend code (one time activity):
bash ../proto-gen.sh
-
Run the development server:
yarn 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.