Wav2vec2 Base 960h

🚀 Wav2Vec2 Base 960h with ONNX for Transformers.js

This project provides the ONNX weights of the facebook/wav2vec2-base-960h model to make it compatible with Transformers.js. It enables seamless speech recognition in JavaScript environments.

🚀 Quick Start

📦 Installation

If you haven't already, you can install the Transformers.js JavaScript library from NPM using the following command:

npm i @xenova/transformers

💻 Usage Examples

Basic Usage

You can use the model for speech recognition with the following code:

import { pipeline } from '@xenova/transformers';

// Create an Automatic Speech Recognition pipeline
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/wav2vec2-base-960h');

// Transcribe audio
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);
// { text: 'AND SO MY FELLOW AMERICAN AND NOT WHAT YOUR COUNTRY CAN DO FOR YOU AND WHAT YOU CAN DO FOR YOUR COUNTRY' }

⚠️ Important Note

Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).