moonshine-web-vue / README.md
nekomeowww's picture
release: build 6d403034d03d101dc3aaf30a938d5f9f61b0730e
de27836
metadata
emoji: 🌙
sdk: static
pinned: false
license: mit
title: Moonshine Web (Vue)
colorFrom: yellow
colorTo: yellow
models:
  - onnx-community/moonshine-base-ONNX
short_description: Yet another Real-time in-browser STT, re-implemented in Vue
thumbnail: >-
  https://raw.githubusercontent.com/moeru-ai/airi/refs/heads/main/packages/moonshine-web/public/banner.png

Moonshine Web (Vue)

[Try it]

Heavily inspired by Realtime in-browser speech recognition

Moonshine Web

A simple Vue + Vite application for running Moonshine Base, a powerful speech-to-text model optimized for fast and accurate automatic speech recognition (ASR) on resource-constrained devices. It runs locally in the browser using Transformers.js and WebGPU-acceleration (or WASM as a fallback).

Getting Started

Follow the steps below to set up and run the application.

1. Clone the Repository

Clone the examples repository from GitHub:

git clone https://github.com/moeru-ai/airi.git

2. Navigate to the Project Directory

Change your working directory to the moonshine-web folder:

cd packages/moonshine-web

3. Install Dependencies

Install the necessary dependencies using npm:

npm i

4. Run the Development Server

Start the development server:

npm run dev

The application should now be running locally. Open your browser and go to http://localhost:5175 to see it in action.

Acknowledgements

The audio visualizer was adapted from Wael Yasmina's amazing tutorial.

Great thanks to what Xenova have done.

Source code