Update README.md

README.md

@@ -6,4 +6,74 @@ tags:
 
 https://huggingface.co/laion/larger_clap_general 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/@xenova/transformers) using:
+```bash
+npm i @xenova/transformers
+```
+
+**Example:** Perform zero-shot audio classification with `Xenova/larger_clap_general`.
+```js
+import { pipeline } from '@xenova/transformers';
+
+const classifier = await pipeline('zero-shot-audio-classification', 'Xenova/larger_clap_general');
+
+const audio = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/piano.wav';
+const candidate_labels = ['calm piano music', 'heavy metal music'];
+const scores = await classifier(audio, candidate_labels);
+// [
+//   { score: 0.9829504489898682, label: 'calm piano music' },
+//   { score: 0.017049523070454597, label: 'heavy metal music' }
+// ]
+```
+
+**Example:** Compute text embeddings with `ClapTextModelWithProjection`.
+
+```js
+import { AutoTokenizer, ClapTextModelWithProjection } from '@xenova/transformers';
+
+// Load tokenizer and text model
+const tokenizer = await AutoTokenizer.from_pretrained('Xenova/larger_clap_general');
+const text_model = await ClapTextModelWithProjection.from_pretrained('Xenova/larger_clap_general');
+
+// Run tokenization
+const texts = ['calm piano music', 'heavy metal music'];
+const text_inputs = tokenizer(texts, { padding: true, truncation: true });
+
+// Compute embeddings
+const { text_embeds } = await text_model(text_inputs);
+// Tensor {
+//   dims: [ 2, 512 ],
+//   type: 'float32',
+//   data: Float32Array(1024) [ ... ],
+//   size: 1024
+// }
+```
+
+**Example:** Compute audio embeddings with `ClapAudioModelWithProjection`.
+```js
+import { AutoProcessor, ClapAudioModelWithProjection, read_audio } from '@xenova/transformers';
+
+// Load processor and audio model
+const processor = await AutoProcessor.from_pretrained('Xenova/larger_clap_general');
+const audio_model = await ClapAudioModelWithProjection.from_pretrained('Xenova/larger_clap_general');
+
+// Read audio and run processor
+const audio = await read_audio('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/piano.wav');
+const audio_inputs = await processor(audio);
+
+// Compute embeddings
+const { audio_embeds } = await audio_model(audio_inputs);
+// Tensor {
+//   dims: [ 1, 512 ],
+//   type: 'float32',
+//   data: Float32Array(512) [ ... ],
+//   size: 512
+// }
+```
+
+---
+
+
 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`).