Add support for Moonshine ASR

[xenova]

This PR adds support for Moonshine, a family of speech-to-text models optimized for fast and accurate automatic speech recognition (ASR) on resource-constrained devices. They are well-suited to real-time, on-device applications like live transcription and voice command recognition, and will be perfect for in-browser usage. This PR is using a dev branch of transformers by @eustlb (huggingface/transformers#34784), and a dev branch of Optimum for ONNX conversion.

• https://huggingface.co/onnx-community/moonshine-tiny-ONNX
• https://huggingface.co/onnx-community/moonshine-base-ONNX

Example usage:

With pipeline API:

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

const transcriber = await pipeline("automatic-speech-recognition", "onnx-community/moonshine-tiny-ONNX");
const output = await transcriber("https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav");
console.log(output);
// { text: 'And so my fellow Americans ask not what your country can do for you as what you can do for your country.' }

Without pipeline API:

import { MoonshineForConditionalGeneration, AutoProcessor, read_audio } from "@huggingface/transformers";

// Load model and processor
const model_id = "onnx-community/moonshine-tiny-ONNX";
const model = await MoonshineForConditionalGeneration.from_pretrained(model_id, {
    dtype: "q4",
});
const processor = await AutoProcessor.from_pretrained(model_id);

// Load audio and prepare inputs
const audio = await read_audio("https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav", 16000);
const inputs = await processor(audio);

// Generate outputs
const outputs = await model.generate({ ...inputs, max_new_tokens: 100 });

// Decode outputs
const decoded = processor.batch_decode(outputs, { skip_special_tokens: true });
console.log(decoded[0]);
// And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.

closes #990

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[xenova]

Model works with WebGPU too, and I've adapted this real-time demo to work with model. Significantly faster than the whisper version. 🔥