Update README.md

README.md

@@ -5,4 +5,32 @@ library_name: transformers.js
 
 https://huggingface.co/superb/wav2vec2-base-superb-ks with ONNX weights to be compatible with Transformers.js.
 
+
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+**Example:** Perform audio classification with `Xenova/wav2vec2-base-superb-ks` and return top 3 results.
+```js
+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(await read_audio(url), { top_k: 3});
+console.log(output);
+// [
+//   { label: 'down', score: 0.9998697638511658 },
+//   { label: 'go', score: 0.00009957332076737657 },
+//   { label: '_unknown_', score: 0.000029320701287360862 },
+// ]
+```
+
+---
+
 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](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).