https://github.com/mikeesto/whimscribe
Private audio transcription with Cohere Transcribe and transformers.js
https://github.com/mikeesto/whimscribe
cohere-transcribe speech-to-text sveltekit transcription transformers-js webgpu
Last synced: 3 days ago
JSON representation
Private audio transcription with Cohere Transcribe and transformers.js
- Host: GitHub
- URL: https://github.com/mikeesto/whimscribe
- Owner: mikeesto
- Created: 2026-04-06T11:00:00.000Z (2 months ago)
- Default Branch: master
- Last Pushed: 2026-05-15T07:21:26.000Z (about 1 month ago)
- Last Synced: 2026-05-15T09:30:52.257Z (about 1 month ago)
- Topics: cohere-transcribe, speech-to-text, sveltekit, transcription, transformers-js, webgpu
- Language: Svelte
- Homepage: https://whimscribe.netlify.app/
- Size: 69.3 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Whimscribe
A browser based audio transcription app. Drop in an audio file and get a transcript — all processing runs locally in the browser via WebGPU using the [Cohere Transcribe](https://huggingface.co/onnx-community/cohere-transcribe-03-2026-ONNX) model.
## Getting started
```sh
npm install
npm run dev
```
## Requirements
A browser with WebGPU support. The model (~2 GB) is downloaded on first use and cached by the browser.