xenova/whisper-web
ML-powered speech recognition directly in your browser
Leverages Transformers.js to run OpenAI's Whisper model entirely client-side without server dependencies. Supports multiple languages and includes experimental WebGPU acceleration for GPU-backed inference. Built as a web application deployable on static hosting, with Web Worker support for non-blocking audio processing.
3,257 stars. No commits in the last 6 months.
Stars
3,257
Forks
421
Language
TypeScript
License
MIT
Category
Last pushed
Oct 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/xenova/whisper-web"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
linto-ai/whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
argmaxinc/WhisperKit
On-device Speech Recognition for Apple Silicon
yeyupiaoling/Whisper-Finetune
Fine-tune the Whisper speech recognition model to support training without timestamp data,...
vasistalodagala/whisper-finetune
Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets...
Pikurrot/whisper-gui
A simple GUI to use Whisper.