transformers.js/pr_1113/en/guides/node-audio-processing.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Server-side Audio Processing in Node.js&quot;,&quot;local&quot;:&quot;server-side-audio-processing-in-nodejs&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Prerequisites&quot;,&quot;local&quot;:&quot;prerequisites&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Getting started&quot;,&quot;local&quot;:&quot;getting-started&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Creating the application&quot;,&quot;local&quot;:&quot;creating-the-application&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/transformers.js/pr_1113/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/entry/start.88a6e140.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/scheduler.0219f8bd.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/singletons.c59c6d8d.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/paths.8e090985.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/entry/app.0003020d.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/index.f61edf3b.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/nodes/0.25c65ab2.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/nodes/25.ddea1085.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/Tip.5d1e3ef4.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/CodeBlock.38e566ae.js">
		<link rel="modulepreload" href="/docs/transformers.js/pr_1113/en/_app/immutable/chunks/EditOnGithub.48fa589f.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Server-side Audio Processing in Node.js&quot;,&quot;local&quot;:&quot;server-side-audio-processing-in-nodejs&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Prerequisites&quot;,&quot;local&quot;:&quot;prerequisites&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Getting started&quot;,&quot;local&quot;:&quot;getting-started&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Creating the application&quot;,&quot;local&quot;:&quot;creating-the-application&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="server-side-audio-processing-in-nodejs" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#server-side-audio-processing-in-nodejs"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Server-side Audio Processing in Node.js</span></h1> <p data-svelte-h="svelte-ga23p1">A major benefit of writing code for the web is that you can access the multitude of APIs that are available in modern browsers. Unfortunately, when writing server-side code, we are not afforded such luxury, so we have to find another way. In this tutorial, we will design a simple Node.js application that uses Transformers.js for speech recognition with <a href="https://huggingface.co/Xenova/whisper-tiny.en" rel="nofollow">Whisper</a>, and in the process, learn how to process audio on the server.</p> <p data-svelte-h="svelte-1p7qc0w">The main problem we need to solve is that the <a href="https://developer.mozilla.org/en-US/docs/Web/API/Web_Audio_API" rel="nofollow">Web Audio API</a> is not available in Node.js, meaning we can’t use the <a href="https://developer.mozilla.org/en-US/docs/Web/API/AudioContext" rel="nofollow"><code>AudioContext</code></a> class to process audio. So, we will need to install third-party libraries to obtain the raw audio data. For this example, we will only consider <code>.wav</code> files, but the same principles apply to other audio formats.</p>  <div class="course-tip  bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-19bu2gi">This tutorial will be written as an ES module, but you can easily adapt it to use CommonJS instead. For more information, see the <a href="https://huggingface.co/docs/transformers.js/tutorials/node" rel="nofollow">node tutorial</a>.</p></div> <p data-svelte-h="svelte-1kriz5m"><strong>Useful links:</strong></p> <ul data-svelte-h="svelte-gjomd0"><li><a href="https://github.com/huggingface/transformers.js/tree/main/examples/node-audio-processing" rel="nofollow">Source code</a></li> <li><a href="https://huggingface.co/docs/transformers.js" rel="nofollow">Documentation</a></li></ul>  <h2 class="relative group"><a id="prerequisites" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#prerequisites"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Prerequisites</span></h2> <ul data-svelte-h="svelte-1qy4daj"><li><a href="https://nodejs.org/en/" rel="nofollow">Node.js</a> version 18+</li> <li><a href="https://www.npmjs.com/" rel="nofollow">npm</a> version 9+</li></ul>  <h2 class="relative group"><a id="getting-started" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#getting-started"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Getting started</span></h2> <p data-svelte-h="svelte-1xetp1f">Let’s start by creating a new Node.js project and installing Transformers.js via <a href="https://www.npmjs.com/package/@huggingface/transformers" rel="nofollow">NPM</a>:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->npm init -y
npm i @huggingface/transformers<!-- HTML_TAG_END --></pre></div>  <div class="course-tip  bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1hk65wu">Remember to add <code>&quot;type&quot;: &quot;module&quot;</code> to your <code>package.json</code> to indicate that your project uses ECMAScript modules.</p></div> <p data-svelte-h="svelte-e9y8ng">Next, let’s install the <a href="https://www.npmjs.com/package/wavefile" rel="nofollow"><code>wavefile</code></a> package, which we will use for loading <code>.wav</code> files:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->npm i wavefile<!-- HTML_TAG_END --></pre></div>  <h2 class="relative group"><a id="creating-the-application" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#creating-the-application"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Creating the application</span></h2> <p data-svelte-h="svelte-wc1j2">Start by creating a new file called <code>index.js</code>, which will be the entry point for our application. Let’s also import the necessary modules:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { pipeline } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">import</span> wavefile <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;wavefile&#x27;</span>;<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-g3d4hf">For this tutorial, we will use the <code>Xenova/whisper-tiny.en</code> model, but feel free to choose one of the other whisper models from the <a href="https://huggingface.co/models?library=transformers.js&search=whisper" rel="nofollow">Hugging Face Hub</a>. Let’s create our pipeline with:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">let</span> transcriber = <span class="hljs-keyword">await</span> <span class="hljs-title function_">pipeline</span>(<span class="hljs-string">&#x27;automatic-speech-recognition&#x27;</span>, <span class="hljs-string">&#x27;Xenova/whisper-tiny.en&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1jpls9q">Next, let’s load an audio file and convert it to the format required by Transformers.js:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment">// Load audio data</span>
<span class="hljs-keyword">let</span> url = <span class="hljs-string">&#x27;https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav&#x27;</span>;
<span class="hljs-keyword">let</span> buffer = <span class="hljs-title class_">Buffer</span>.<span class="hljs-title function_">from</span>(<span class="hljs-keyword">await</span> <span class="hljs-title function_">fetch</span>(url).<span class="hljs-title function_">then</span>(<span class="hljs-function"><span class="hljs-params">x</span> =&gt;</span> x.<span class="hljs-title function_">arrayBuffer</span>()))

<span class="hljs-comment">// Read .wav file and convert it to required format</span>
<span class="hljs-keyword">let</span> wav = <span class="hljs-keyword">new</span> wavefile.<span class="hljs-title class_">WaveFile</span>(buffer);
wav.<span class="hljs-title function_">toBitDepth</span>(<span class="hljs-string">&#x27;32f&#x27;</span>); <span class="hljs-comment">// Pipeline expects input as a Float32Array</span>
wav.<span class="hljs-title function_">toSampleRate</span>(<span class="hljs-number">16000</span>); <span class="hljs-comment">// Whisper expects audio with a sampling rate of 16000</span>
<span class="hljs-keyword">let</span> audioData = wav.<span class="hljs-title function_">getSamples</span>();
<span class="hljs-keyword">if</span> (<span class="hljs-title class_">Array</span>.<span class="hljs-title function_">isArray</span>(audioData)) {
  <span class="hljs-keyword">if</span> (audioData.<span class="hljs-property">length</span> &gt; <span class="hljs-number">1</span>) {
    <span class="hljs-keyword">const</span> <span class="hljs-variable constant_">SCALING_FACTOR</span> = <span class="hljs-title class_">Math</span>.<span class="hljs-title function_">sqrt</span>(<span class="hljs-number">2</span>);

    <span class="hljs-comment">// Merge channels (into first channel to save memory)</span>
    <span class="hljs-keyword">for</span> (<span class="hljs-keyword">let</span> i = <span class="hljs-number">0</span>; i &lt; audioData[<span class="hljs-number">0</span>].<span class="hljs-property">length</span>; ++i) {
      audioData[<span class="hljs-number">0</span>][i] = <span class="hljs-variable constant_">SCALING_FACTOR</span> * (audioData[<span class="hljs-number">0</span>][i] + audioData[<span class="hljs-number">1</span>][i]) / <span class="hljs-number">2</span>;
    }
  }

  <span class="hljs-comment">// Select first channel</span>
  audioData = audioData[<span class="hljs-number">0</span>];
}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1sjiopi">Finally, let’s run the model and measure execution duration.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">let</span> start = performance.<span class="hljs-title function_">now</span>();
<span class="hljs-keyword">let</span> output = <span class="hljs-keyword">await</span> <span class="hljs-title function_">transcriber</span>(audioData);
<span class="hljs-keyword">let</span> end = performance.<span class="hljs-title function_">now</span>();
<span class="hljs-variable language_">console</span>.<span class="hljs-title function_">log</span>(<span class="hljs-string">`Execution duration: <span class="hljs-subst">${(end - start) / <span class="hljs-number">1000</span>}</span> seconds`</span>);
<span class="hljs-variable language_">console</span>.<span class="hljs-title function_">log</span>(output);<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-cx7eio">You can now run the application with <code>node index.js</code>. Note that when running the script for the first time, it may take a while to download and cache the model. Subsequent requests will use the cached model, and model loading will be much faster.</p> <p data-svelte-h="svelte-s5mxam">You should see output similar to:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->Execution duration: <span class="hljs-number">0.6460317999720574</span> seconds
{
  text: &#x27; And so my fellow Americans ask not what your country can <span class="hljs-keyword">do</span> <span class="hljs-keyword">for</span> <span class="hljs-title class_">you</span>. Ask what you can <span class="hljs-keyword">do</span> <span class="hljs-keyword">for</span> <span class="hljs-title class_">your</span> country.&#x27;
}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1mxb03j">That’s it! You’ve successfully created a Node.js application that uses Transformers.js for speech recognition with Whisper. You can now use this as a starting point for your own applications.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers.js/blob/main/docs/source/guides/node-audio-processing.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_kuyevp = {
						assets: "/docs/transformers.js/pr_1113/en",
						base: "/docs/transformers.js/pr_1113/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/transformers.js/pr_1113/en/_app/immutable/entry/start.88a6e140.js"),
						import("/docs/transformers.js/pr_1113/en/_app/immutable/entry/app.0003020d.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 25],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>