Wav2vec2 Base Superb Ks

🚀 Wav2Vec2 Base Superb KS for Transformers.js

This project provides the ONNX weights of the superb/wav2vec2-base-superb-ks model to make it compatible with Transformers.js.

🚀 Quick Start

The model from https://huggingface.co/superb/wav2vec2-base-superb-ks comes with ONNX weights to be compatible with Transformers.js.

📦 Installation

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

npm i @huggingface/transformers

💻 Usage Examples

Basic Usage

Perform audio classification with Xenova/wav2vec2-base-superb-ks and return top 3 results.

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

// Create an audio classification pipeline
const classifier = await pipeline('audio-classification', 'Xenova/wav2vec2-base-superb-ks');

// Predict class
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/speech-commands_down.wav';
const output = await classifier(url, { top_k: 3 });
console.log(output);
// [
//   { label: 'down', score: 0.9998697638511658 },
//   { label: 'go', score: 0.00009957332076737657 },
//   { label: '_unknown_', score: 0.000029320701287360862 },
// ]

📚 Documentation

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).