Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/xenova/whisper-web
ML-powered speech recognition directly in your browser
https://github.com/xenova/whisper-web
javascript transformers whisper
Last synced: 3 days ago
JSON representation
ML-powered speech recognition directly in your browser
- Host: GitHub
- URL: https://github.com/xenova/whisper-web
- Owner: xenova
- License: mit
- Created: 2023-03-17T17:41:18.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-01T11:32:32.000Z (3 months ago)
- Last Synced: 2024-12-11T21:03:35.109Z (10 days ago)
- Topics: javascript, transformers, whisper
- Language: TypeScript
- Homepage: https://hf.co/spaces/Xenova/whisper-web
- Size: 1.03 MB
- Stars: 2,639
- Watchers: 22
- Forks: 287
- Open Issues: 33
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- AiTreasureBox - xenova/whisper-web - 12-20_2659_0](https://img.shields.io/github/stars/xenova/whisper-web.svg)|ML-powered speech recognition directly in your browser| (Repos)
README
# Whisper Web
ML-powered speech recognition directly in your browser! Built with [🤗 Transformers.js](https://github.com/xenova/transformers.js).
Check out the demo site [here](https://huggingface.co/spaces/Xenova/whisper-web).
> [!IMPORTANT]
> Experimental WebGPU support has been added to [this branch](https://github.com/xenova/whisper-web/tree/experimental-webgpu) ([demo](https://huggingface.co/spaces/Xenova/whisper-webgpu)), 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:
```bash
git clone https://github.com/xenova/whisper-web.git
cd whisper-web
npm install
```2. Run the development server:
```bash
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](https://github.com/xenova/whisper-web/issues/8) for more details.3. Open the link (e.g., [http://localhost:5173/](http://localhost:5173/)) in your browser.