16 lines
652 B
Markdown
16 lines
652 B
Markdown
# Overview
|
|
- A speech recognizer built on Vosk that can be run on the browser, inspired by [vosk-browser](https://github.com/ccoreilly/vosk-browser), but built from scratch and no code taken!
|
|
- Designed with strong exception safety
|
|
- See the usage folder's README.md for API documentation and important notes
|
|
- See the devel folder for the newest build (not guaranteed to work) and the JS build script
|
|
|
|
# Additions to vosk-browser:
|
|
- Download multiple models
|
|
- Model storage path management (for multiple models)
|
|
- Model ID management (for model updates)
|
|
- Smaller JS size (>5.7MB vs 3.9MB)
|
|
- All files are merged into a single bundle.
|
|
|
|
# Basic usage
|
|
|