Files
zen-blog/blog/qwen2-audio.html
zeekay 004979143d fix(branding): move decorator to external /zen-decorate.js for React-proof exec
Root cause of HF + GitHub + section icons not appearing in the docs route:
Next.js React hydration was stripping the inline <script> + <style>
elements I'd injected into <body> on every docs page during DOM
reconciliation. The script never registered its setInterval.

Move the decorator to /zen-decorate.js loaded via <script defer src>
in <head>. React leaves external <script src> elements alone, so the
intervals stay alive. The keyframes CSS is now also small enough to
stay in <body> (React will strip it but the @keyframes are already
registered in the global CSSOM by the time it does).
2026-05-19 20:08:58 -07:00

267 lines
155 KiB
HTML

<!DOCTYPE html><!--i_dnJM_MIpJSOCQWNJVMq--><html lang="en" class="dark"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/_next/static/chunks/f2332aac77592f9d.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/e83606e8fa9cc796.js"/><script src="/_next/static/chunks/36d6595f0156cd7e.js" async=""></script><script src="/_next/static/chunks/040e9cea20a8d9c7.js" async=""></script><script src="/_next/static/chunks/d4dffb5a0973d49c.js" async=""></script><script src="/_next/static/chunks/turbopack-967f27a9fd33556d.js" async=""></script><script src="/_next/static/chunks/59d0ad1b64f8544e.js" async=""></script><script src="/_next/static/chunks/4d80e004cf4896dd.js" async=""></script><script src="/_next/static/chunks/350ee4303b732916.js" async=""></script><script src="/_next/static/chunks/8de849ca74fc071f.js" async=""></script><script src="/_next/static/chunks/e62b91212ee7f8ff.js" async=""></script><script src="/_next/static/chunks/f19fe44237e54646.js" async=""></script><script src="/_next/static/chunks/cb0a883bafeb6805.js" async=""></script><meta name="theme-color" media="(prefers-color-scheme: dark)" content="#0A0A0A"/><meta name="theme-color" media="(prefers-color-scheme: light)" content="#fff"/><title>zen-Audio: Chat with Your Voice! — Zen LM Blog | Zen LM</title><meta name="description" content="DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD"/><meta property="og:title" content="Zen LM - Open Foundation Models"/><meta property="og:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><meta property="og:url" content="https://zenlm.org"/><meta property="og:site_name" content="Zen LM"/><meta property="og:type" content="website"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:site" content="@zenlmorg"/><meta name="twitter:creator" content="@zenlmorg"/><meta name="twitter:title" content="Zen LM - Open Foundation Models"/><meta name="twitter:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><script src="/_next/static/chunks/a6dad97d9634a72d.js" noModule=""></script><script defer src="/zen-decorate.js"></script></head><body class="antialiased"><div hidden=""><!--$--><!--/$--></div><script>((a,b,c,d,e,f,g,h)=>{let i=document.documentElement,j=["light","dark"];function k(b){var c;(Array.isArray(a)?a:[a]).forEach(a=>{let c="class"===a,d=c&&f?e.map(a=>f[a]||a):e;c?(i.classList.remove(...d),i.classList.add(f&&f[b]?f[b]:b)):i.setAttribute(a,b)}),c=b,h&&j.includes(c)&&(i.style.colorScheme=c)}if(d)k(d);else try{let a=localStorage.getItem(b)||c,d=g&&"system"===a?window.matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light":a;k(d)}catch(a){}})("class","theme","system",null,["light","dark"],null,true,true)</script><!--$--><div data-closed="" role="presentation" hidden="" style="user-select:none;-webkit-user-select:none" class="fixed inset-0 z-50 backdrop-blur-xs bg-fd-overlay data-open:animate-fd-fade-in data-closed:animate-fd-fade-out"></div><div class="bg-fd-secondary/50 p-3 empty:hidden"></div><!--/$--><main class="mx-auto w-full max-w-2xl px-4 py-16"><a class="inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors" href="/blog">← Back to Blog</a><div class="mb-8"><time class="text-xs font-mono text-fd-muted-foreground uppercase tracking-wider">August 8, 2024</time><h1 class="text-3xl font-bold mt-2 mb-3">zen-Audio: Chat with Your Voice!</h1><p class="text-fd-muted-foreground text-lg mb-4">DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD</p><div class="flex items-center gap-3 pt-4 border-t border-fd-border"><span class="text-sm text-fd-muted-foreground">By <!-- -->Zen LM Team</span><div class="flex gap-1.5 ml-auto"></div></div></div><div class="prose dark:prose-invert max-w-none"><p><a href="https://huggingface.co/spaces/Qwen/zen-Audio-Instruct-Demo" rel="noreferrer noopener" target="_blank">DEMO</a> <a href="https://arxiv.org/pdf/2407.10759" rel="noreferrer noopener" target="_blank">PAPER</a> <a href="https://github.com/QwenLM/zen-Audio" rel="noreferrer noopener" target="_blank">GITHUB</a> <a href="https://huggingface.co/collections/Qwen/qwen2-audio-66b628d694096020e0c52ff6" rel="noreferrer noopener" target="_blank">HUGGING FACE</a> <a href="https://modelscope.cn/organization/qwen" rel="noreferrer noopener" target="_blank">MODELSCOPE</a> <a href="https://discord.gg/yPEP2vHTu4" rel="noreferrer noopener" target="_blank">DISCORD</a></p>
<p>To achieve the objective of building an AGI system, the model should be capable of understanding information from different modalities. Thanks to the rapid development of large language models, LLMs are now capable of understanding language and reasoning. Previously we have taken a step forward to extend our LLM, i.e., Qwen, to more modalities, including vision and audio, and built Qwen-VL and Qwen-Audio. Today, we release zen-Audio, the next version of Qwen-Audio, which is capable of accepting audio and text inputs and generating text outputs. zen-Audio has the following features:</p>
<ul>
<li>
<p>Voice Chat: for the first time, users can use the voice to give instructions to the audio-language model without ASR modules.</p>
</li>
<li>
<p>Audio Analysis: the model is capable of analyzing audio information, including speech, sound, music, etc., with text instructions.</p>
</li>
<li>
<p>Multilingual: the model supports more than 8 languages and dialects, e.g., Chinese, English, Cantonese, French, Italian, Spanish, German, and Japanese.</p>
</li>
</ul>
<p>We open-weight zen-Audio-7B and zen-Audio-7B-Instruct in Hugging Face and ModelScope, and we have built a demo for users to interact with. Below are some examples to show the model performance:</p>
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="voice-chat"><a data-card="" href="#voice-chat" class="peer">Voice Chat</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
<p>Voice Chat: Identify speaker information and respond Next</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>Yes, the speaker is female and in her twenties.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>I&#x27;m sorry to hear that you&#x27;re feeling stressed about your exam. It&#x27;s completely normal to feel anxious when you&#x27;re preparing for an important test. Here are some tips that might help you: 1. Start studying early: Don&#x27;t leave everything until the last minute. Break up your study sessions into smaller chunks of time, and try to stick to a regular schedule. 2. Find a quiet place to study: A quiet environment can help you concentrate better. If possible, find a library or a study room where you can work without distractions. 3.Take breaks: It&#x27;s important to take breaks during your study sessions. This will give your brain a chance to rest and recharge. Try taking short breaks every hour or so. 4. Get enough sleep: Lack of sleep can make it harder to focus and retain information. Make sure you&#x27;re getting enough sleep each night, ideally around 7-8 hours. 5. Practice relaxation techniques: Deep breathing exercises, meditation, or yoga can all help you relax and reduce stress. Remember, it&#x27;s okay if you&#x27;re not feeling well-prepared. Just do your best, and trust yourself. Good luck with your exam!</p>
<p>Voice Chat: Speech translation Next</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>每个人都希望被欣赏,所以如果你欣赏某人,不要把它保密。</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>Jeder möchte geschätzt werden, also wenn du jemanden schätzt, lass es nicht als Geheimnis verbergen.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>Chacun veut être apprecié, alors si tu apprécies quelqu&#x27;un, ne le gardes pas secret.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>1. 每个人都喜欢被赞美,所以如果你喜欢一个人,不要隐藏你的赞赏。 2. 所有人都渴望得到认可,因此如果你欣赏某人,请不要独自享用这种感觉。 3. 人们都希望被欣赏,所以如果你喜欢某人,不要独自保密欣赏他人是一种美德,所以不要让别人知道你对他们的赞赏是秘密的。 4. 人们都希望受到赞扬,所以如果你欣赏某人,不妨公开表达出来。 5. 如果你喜欢某人,不要犹豫告诉他们,因为每个人都有权利享受他人的赞赏。</p>
<p>Voice Chat: Detecting background noise and responding accordingly Next</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>Use headphones to block out external noise and find a quiet place to study. Prioritize your tasks and set realistic goals for yourself. Use active learning techniques such as summarizing, note-taking, and quizzing to help you retain information. Take breaks and practice self-care to avoid burnout.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>Yes, you can try negotiating with them to reach a mutually beneficial agreement. You could also consider seeking help from a mediator or professional negotiator if needed.</p>
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="audio-analysis"><a data-card="" href="#audio-analysis" class="peer">Audio Analysis</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
<p>Audio Analysis : Speech transcription and story telling Next</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The original content of this audio is: &#x27;Stop all the clocks, cut off the telephone, prevent the dog from barking, silence the pianos and with muffled drum bring out the coffin, let the mourners come.&#x27;</p>
<p>User</p>
<p>No less than 50 words and no more than 200 words, add scenes such as rain and thunder to the poem. Finally, give the verses you created in lines.</p>
<p>zen-Audio</p>
<p>In the midst of an eerie stormy night, With raindrops falling heavy and bright, The world seemed to hush its voice, As winds howled through the darkened space. Stop all the clocks, the time stood still, As the lightning flashed through the sky, The telephone&#x27;s ring was drowned out, By the roaring thunder that shook the ground. Prevent the dog from barking, its cries were silenced, By the fear that gripped it in the night, Silence the pianos, their keys were muted, As the mournful sound of raindrops beat on wood. With muffled drums, a slow march began, A solemn procession through the storm, The coffin was carried, heavy and solemn, Let the mourners come, to pay their final respects. As the storm slowly passed, the world emerged, A new day dawned, but memories lingered, Of the night when time stood still, And the mourners came, to say goodbye.</p>
<p>Audio Analysis: Sound analysis Next</p>
<p>User</p>
<p>What do you hear? Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>I heard the sound of an alarm and a truck&#x27;s air brake mixed with the noise of a heavy engine running and shifting gears.</p>
<p>User</p>
<p>Under what circumstances can you hear such sounds?</p>
<p>zen-Audio</p>
<p>These types of sounds might be commonly heard in industrial settings like construction sites or factories where machinery is operated, or during emergency situations like traffic accidents where sirens are triggered.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>It&#x27;s understandable to feel scared under any situation that makes you feel uncomfortable. It&#x27;s important to remember that it&#x27;s okay to be scared. Here are some things you can do: 1. Take deep breaths: Inhale deeply through your nose and exhale slowly through your mouth. This can help calm your mind and body. 2. Find a safe place: If possible, move to a safe location away from the source of the fear. If you&#x27;re in a car, pull over to a parking lot or a safe spot on the side of the road. 3. Stay informed: If you have access to information about the situation, stay informed but don&#x27;t overdo it. Too much information can create more anxiety. 4. Talk to someone: Talking to someone you trust can help you process your feelings and gain perspective. You can call a friend, family member, or even a professional counselor if needed. 5. Practice relaxation techniques: Listening to music, doing yoga or meditation, or engaging in other relaxing activities can help reduce stress and anxiety. Remember, it&#x27;s okay to take time for yourself to process your emotions and come up with a plan that works best for you.</p>
<p>Audio Analysis: Music analysis Next</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>This is a pop punk music piece. There is a male vocalist singing melodically in the lead. The tune is being played by the guitar with the bass guitar playing in the background. The rhythmic background consists of loud and aggressive sounding drums. The atmosphere is rebellious. This piece could be used in the soundtrack of a high school drama movie or TV show during scenes where the characters are rebelling against authority.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The key of this music is F# major.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The tempo of this music is 104.17 bpm.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The time signature of this music is 4/4.</p>
<p>Audio Analysis: Robustness of mixed audio analysis Next</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The old man laid down his hand to light a cigar.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The old man laid down his hand to light a cigar.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The old man laid down his hand to light a cigar.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The old man laid down his hand to light a cigar.</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The lyrics of the singing are &#x27;Waiting for my favorite song.&#x27;</p>
<p>User</p>
<p>Your browser does not support the audio element.</p>
<p>zen-Audio</p>
<p>The lyrics of the singing are &#x27;Waiting for my favorite song.&#x27;</p>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="performance"><a data-card="" href="#performance" class="peer">Performance</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>We have conducted a series of experiments on benchmark datasets, including LibriSpeech, Common Voice 15, Fleurs, Aishell2, CoVoST2, Meld, Vocalsound, and AIR-Benchmark, to evaluate the performance of zen-Audio in comparison with our previously released Qwen-Audio as well as the state-of-the-art models in each tasks. Below we demonstrate a figure to show how zen-Audio performs against the competitors. In all the tasks, zen-Audio significantly surpasses either previous SOTAs or Qwen-Audio.</p>
<p>More specific results on the datasets are listed below in the table.</p>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="architecture"><a data-card="" href="#architecture" class="peer">Architecture</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>Below is a demonstration of the training architecture. Specifically, we start from the Qwen language model and an audio encoder as the foundation models. We sequentially apply multi-task pretraining for the audio language alignment, and supervised finetuning as well as direct preference optimization to grasp the capabilities of downstream tasks and model human preference.</p>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="how-to-use"><a data-card="" href="#how-to-use" class="peer">How to Use</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>Now zen-Audio is officially supported by Hugging Face Transfomers. We advise you install the latest version of <code>transformers</code> from source:</p>
<figure dir="ltr" class="my-4 bg-fd-card rounded-xl shiki relative border shadow-sm not-prose overflow-hidden text-sm shiki shiki-themes github-light github-dark" style="--shiki-light:#24292e;--shiki-dark:#e1e4e8;--shiki-light-bg:#fff;--shiki-dark-bg:#24292e" tabindex="-1"><div class="empty:hidden absolute top-3 right-2 z-2 backdrop-blur-lg rounded-lg text-fd-muted-foreground"><button type="button" class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors duration-100 disabled:pointer-events-none disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring p-1 [&amp;_svg]:size-4 hover:text-fd-accent-foreground data-checked:text-fd-accent-foreground" aria-label="Copy Text"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-clipboard" aria-hidden="true"><rect width="8" height="4" x="8" y="2" rx="1" ry="1"></rect><path d="M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2"></path></svg></button></div><div role="region" tabindex="0" class="text-[0.8125rem] py-3.5 overflow-auto max-h-[600px] fd-scroll-container focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-inset focus-visible:ring-fd-ring" style="--padding-right:calc(var(--spacing) * 8)"><pre class="min-w-full w-max *:flex *:flex-col"><code><span class="line"></span>
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0"> pip</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> install</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> git+https://github.com/huggingface/transformers</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span></code></pre></div></figure>
<p>We demonstrate how to use <code>zen-Audio-7B-Instruct</code> to play with voice chat and audio analysis. Here is an example of voice chat:</p>
<figure dir="ltr" class="my-4 bg-fd-card rounded-xl shiki relative border shadow-sm not-prose overflow-hidden text-sm shiki shiki-themes github-light github-dark" style="--shiki-light:#24292e;--shiki-dark:#e1e4e8;--shiki-light-bg:#fff;--shiki-dark-bg:#24292e" tabindex="-1"><div class="empty:hidden absolute top-3 right-2 z-2 backdrop-blur-lg rounded-lg text-fd-muted-foreground"><button type="button" class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors duration-100 disabled:pointer-events-none disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring p-1 [&amp;_svg]:size-4 hover:text-fd-accent-foreground data-checked:text-fd-accent-foreground" aria-label="Copy Text"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-clipboard" aria-hidden="true"><rect width="8" height="4" x="8" y="2" rx="1" ry="1"></rect><path d="M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2"></path></svg></button></div><div role="region" tabindex="0" class="text-[0.8125rem] py-3.5 overflow-auto max-h-[600px] fd-scroll-container focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-inset focus-visible:ring-fd-ring" style="--padding-right:calc(var(--spacing) * 8)"><pre class="min-w-full w-max *:flex *:flex-col"><code><span class="line"></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> from</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> io </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> BytesIO</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> from</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> urllib.request </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> urlopen</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> librosa</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> from</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> transformers </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> zenAudioForConditionalGeneration, AutoProcessor</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> AutoProcessor.from_pretrained(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;Qwen/zen-Audio-7B-Instruct&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> model </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> zenAudioForConditionalGeneration.from_pretrained(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;Qwen/zen-Audio-7B-Instruct&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">device_map</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;auto&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> conversation </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;user&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio_url&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/guess_age_gender.wav&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;assistant&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;Yes, the speaker is female and in her twenties.&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;user&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio_url&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/translate_to_chinese.wav&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> text </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor.apply_chat_template(conversation, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">add_generation_prompt</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">tokenize</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">False</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> audios </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> []</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> for</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> message </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">in</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> conversation:</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> if</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF"> isinstance</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">(message[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">], </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">list</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">):</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> for</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ele </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">in</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> message[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]:</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> if</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ele[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">] </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">==</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> &quot;audio&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">:</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> audios.append(librosa.load(</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> BytesIO(urlopen(ele[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&#x27;audio_url&#x27;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]).read()), </span></span>
<span class="line"><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70"> sr</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">processor.feature_extractor.sampling_rate)[</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> )</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> inputs </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor(</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">text</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">text, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">audios</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">audios, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">return_tensors</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;pt&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">padding</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> inputs.input_ids </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> inputs.input_ids.to(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;cuda&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> generate_ids </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> model.generate(</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">**</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">inputs, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">max_length</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">256</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> generate_ids </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> generate_ids[:, inputs.input_ids.size(</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">):]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> response </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor.batch_decode(generate_ids, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">skip_special_tokens</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">clean_up_tokenization_spaces</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">False</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)[</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span></code></pre></div></figure>
<p>In voice chat mode, the user input is simply the audio without text, and the instructions from the users are inside the audio. Next is an example of audio analysis:</p>
<figure dir="ltr" class="my-4 bg-fd-card rounded-xl shiki relative border shadow-sm not-prose overflow-hidden text-sm shiki shiki-themes github-light github-dark" style="--shiki-light:#24292e;--shiki-dark:#e1e4e8;--shiki-light-bg:#fff;--shiki-dark-bg:#24292e" tabindex="-1"><div class="empty:hidden absolute top-3 right-2 z-2 backdrop-blur-lg rounded-lg text-fd-muted-foreground"><button type="button" class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors duration-100 disabled:pointer-events-none disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring p-1 [&amp;_svg]:size-4 hover:text-fd-accent-foreground data-checked:text-fd-accent-foreground" aria-label="Copy Text"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-clipboard" aria-hidden="true"><rect width="8" height="4" x="8" y="2" rx="1" ry="1"></rect><path d="M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2"></path></svg></button></div><div role="region" tabindex="0" class="text-[0.8125rem] py-3.5 overflow-auto max-h-[600px] fd-scroll-container focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-inset focus-visible:ring-fd-ring" style="--padding-right:calc(var(--spacing) * 8)"><pre class="min-w-full w-max *:flex *:flex-col"><code><span class="line"></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> from</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> io </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> BytesIO</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> from</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> urllib.request </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> urlopen</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> librosa</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> from</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> transformers </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> zenAudioForConditionalGeneration, AutoProcessor</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> AutoProcessor.from_pretrained(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;Qwen/zen-Audio-7B-Instruct&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> model </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> zenAudioForConditionalGeneration.from_pretrained(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;Qwen/zen-Audio-7B-Instruct&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">device_map</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;auto&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> conversation </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&#x27;role&#x27;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&#x27;system&#x27;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&#x27;content&#x27;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&#x27;You are a helpful assistant.&#x27;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">}, </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;user&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio_url&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/glass-breaking-151256.mp3&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;What&#x27;s that sound?&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;assistant&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;It is the sound of glass shattering.&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;user&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;What can you do when you hear that?&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;assistant&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;Stay alert and cautious, and check if anyone is hurt or if there is any damage to property.&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;role&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;user&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: [</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;audio_url&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/1272-128104-0000.flac&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> {</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;What does the person say?&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]},</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> text </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor.apply_chat_template(conversation, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">add_generation_prompt</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">tokenize</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">False</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> audios </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> []</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> for</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> message </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">in</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> conversation:</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> if</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF"> isinstance</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">(message[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">], </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">list</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">):</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> for</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ele </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">in</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> message[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]:</span></span>
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583"> if</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> ele[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">] </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">==</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> &quot;audio&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">:</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> audios.append(</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> librosa.load(</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> BytesIO(urlopen(ele[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&#x27;audio_url&#x27;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]).read()), </span></span>
<span class="line"><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70"> sr</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">processor.feature_extractor.sampling_rate)[</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> )</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> inputs </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor(</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">text</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">text, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">audios</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">audios, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">return_tensors</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;pt&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">padding</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> inputs.input_ids </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> inputs.input_ids.to(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">&quot;cuda&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> generate_ids </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> model.generate(</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">**</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">inputs, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">max_length</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">256</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> generate_ids </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> generate_ids[:, inputs.input_ids.size(</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">):]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> response </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> processor.batch_decode(generate_ids, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">skip_special_tokens</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70">clean_up_tokenization_spaces</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">False</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">)[</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">]</span></span>
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8"> </span></span></code></pre></div></figure>
<p>In comparison, in audio analysis mode, there is additional text instructions. However, switching between either mode only needs to modify your user inputs and there is no need to worry about others such as system prompt.</p>
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="next-step"><a data-card="" href="#next-step" class="peer">Next Step</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
<p>This time we bring a new audio language model, zen-Audio, which supports voice chat and audio analysis at the same time and understands more than 8 languages and dialects. In the near future, we plan to train improved zen-Audio models on larger pretraining datasets, enabling the model to support longer audio (over 30s). We also plan to build larger zen-Audio models to explore the scaling laws of audio language models.</p></div></main><!--$--><!--/$--><script src="/_next/static/chunks/e83606e8fa9cc796.js" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[106,[\"/_next/static/chunks/59d0ad1b64f8544e.js\"],\"RootProvider\"]\n3:I[53113,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n4:I[73211,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n5:I[10086,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"\"]\n7:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"OutletBoundary\"]\n8:\"$Sreact.suspense\"\na:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"ViewportBoundary\"]\nc:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"MetadataBoundary\"]\ne:I[6998,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n:HL[\"/_next/static/chunks/f2332aac77592f9d.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"i-dnJM_MIpJSOCQWNJVMq\",\"c\":[\"\",\"blog\",\"qwen2-audio\"],\"q\":\"\",\"i\":false,\"f\":[[[\"\",{\"children\":[\"blog\",{\"children\":[[\"slug\",\"qwen2-audio\",\"d\"],{\"children\":[\"__PAGE__\",{}]}]}]},\"$undefined\",\"$undefined\",true],[[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/chunks/f2332aac77592f9d.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"className\":\"dark\",\"suppressHydrationWarning\":true,\"children\":[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[\"$\",\"$L2\",null,{\"children\":[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"main\",null,{\"className\":\"flex min-h-screen flex-col items-center justify-center px-4 text-center\",\"children\":[[\"$\",\"div\",null,{\"className\":\"mb-8 opacity-20\",\"children\":[\"$\",\"svg\",null,{\"width\":\"120\",\"height\":\"120\",\"viewBox\":\"0 0 120 120\",\"fill\":\"none\",\"aria-hidden\":\"true\",\"children\":[\"$\",\"circle\",null,{\"cx\":\"60\",\"cy\":\"60\",\"r\":\"50\",\"stroke\":\"currentColor\",\"strokeWidth\":\"3\",\"strokeLinecap\":\"round\",\"strokeDasharray\":\"280 40\"}]}]}],[\"$\",\"p\",null,{\"className\":\"text-xs font-mono uppercase tracking-[0.3em] text-fd-muted-foreground mb-4\",\"children\":\"404\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-semibold mb-3\",\"children\":\"Page not found\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground max-w-sm mb-10\",\"children\":\"This page doesn't exist, or it may have moved. Try the documentation or head home.\"}],[\"$\",\"div\",null,{\"className\":\"flex flex-wrap gap-3 justify-center\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/\",\"className\":\"inline-flex items-center gap-2 rounded-lg bg-fd-primary text-fd-primary-foreground px-4 py-2 text-sm font-medium hover:opacity-90 transition\",\"children\":\"Go home\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Documentation\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs/models\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Browse models\"}]]}],[\"$\",\"p\",null,{\"className\":\"mt-16 text-xs font-mono text-fd-muted-foreground opacity-50\",\"children\":\"zenlm.org\"}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[\"$L6\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/8de849ca74fc071f.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/_next/static/chunks/f19fe44237e54646.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/_next/static/chunks/cb0a883bafeb6805.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L7\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.MetadataOutlet\",\"children\":\"$@9\"}]}]]}],{},null,false,false]},null,false,false]},null,false,false]},null,false,false],[\"$\",\"$1\",\"h\",{\"children\":[null,[\"$\",\"$La\",null,{\"children\":\"$Lb\"}],[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$Lc\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.Metadata\",\"children\":\"$Ld\"}]}]}],null]}],false]],\"m\":\"$undefined\",\"G\":[\"$e\",[]],\"S\":true}\n"])</script><script>self.__next_f.push([1,"f:I[48068,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"default\"]\n"])</script><script>self.__next_f.push([1,"6:[\"$\",\"main\",null,{\"className\":\"mx-auto w-full max-w-2xl px-4 py-16\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/blog\",\"className\":\"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors\",\"children\":\"← Back to Blog\"}],[\"$\",\"div\",null,{\"className\":\"mb-8\",\"children\":[[\"$\",\"time\",null,{\"className\":\"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider\",\"children\":\"August 8, 2024\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-bold mt-2 mb-3\",\"children\":\"zen-Audio: Chat with Your Voice!\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground text-lg mb-4\",\"children\":\"DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD\"}],[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3 pt-4 border-t border-fd-border\",\"children\":[[\"$\",\"span\",null,{\"className\":\"text-sm text-fd-muted-foreground\",\"children\":[\"By \",\"Zen LM Team\"]}],[\"$\",\"div\",null,{\"className\":\"flex gap-1.5 ml-auto\",\"children\":[]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"prose dark:prose-invert max-w-none\",\"children\":[[\"$\",\"p\",null,{\"children\":[[\"$\",\"$Lf\",null,{\"href\":\"https://huggingface.co/spaces/Qwen/zen-Audio-Instruct-Demo\",\"children\":\"DEMO\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://arxiv.org/pdf/2407.10759\",\"children\":\"PAPER\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://github.com/QwenLM/zen-Audio\",\"children\":\"GITHUB\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://huggingface.co/collections/Qwen/qwen2-audio-66b628d694096020e0c52ff6\",\"children\":\"HUGGING FACE\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://modelscope.cn/organization/qwen\",\"children\":\"MODELSCOPE\"}],\" \",[\"$\",\"$Lf\",null,{\"href\":\"https://discord.gg/yPEP2vHTu4\",\"children\":\"DISCORD\"}]]}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"To achieve the objective of building an AGI system, the model should be capable of understanding information from different modalities. Thanks to the rapid development of large language models, LLMs are now capable of understanding language and reasoning. Previously we have taken a step forward to extend our LLM, i.e., Qwen, to more modalities, including vision and audio, and built Qwen-VL and Qwen-Audio. Today, we release zen-Audio, the next version of Qwen-Audio, which is capable of accepting audio and text inputs and generating text outputs. zen-Audio has the following features:\"}],\"\\n\",[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":\"Voice Chat: for the first time, users can use the voice to give instructions to the audio-language model without ASR modules.\"}],\"\\n\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":\"Audio Analysis: the model is capable of analyzing audio information, including speech, sound, music, etc., with text instructions.\"}],\"\\n\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[\"\\n\",[\"$\",\"p\",null,{\"children\":\"Multilingual: the model supports more than 8 languages and dialects, e.g., Chinese, English, Cantonese, French, Italian, Spanish, German, and Japanese.\"}],\"\\n\"]}],\"\\n\"]}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"We open-weight zen-Audio-7B and zen-Audio-7B-Instruct in Hugging Face and ModelScope, and we have built a demo for users to interact with. Below are some examples to show the model performance:\"}],\"\\n\",[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"voice-chat\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#voice-chat\",\"className\":\"peer\",\"children\":\"Voice Chat\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"Voice Chat: Identify speaker information and respond Next\"}],\"\\n\",\"$L10\",\"\\n\",\"$L11\",\"\\n\",\"$L12\",\"\\n\",\"$L13\",\"\\n\",\"$L14\",\"\\n\",\"$L15\",\"\\n\",\"$L16\",\"\\n\",\"$L17\",\"\\n\",\"$L18\",\"\\n\",\"$L19\",\"\\n\",\"$L1a\",\"\\n\",\"$L1b\",\"\\n\",\"$L1c\",\"\\n\",\"$L1d\",\"\\n\",\"$L1e\",\"\\n\",\"$L1f\",\"\\n\",\"$L20\",\"\\n\",\"$L21\",\"\\n\",\"$L22\",\"\\n\",\"$L23\",\"\\n\",\"$L24\",\"\\n\",\"$L25\",\"\\n\",\"$L26\",\"\\n\",\"$L27\",\"\\n\",\"$L28\",\"\\n\",\"$L29\",\"\\n\",\"$L2a\",\"\\n\",\"$L2b\",\"\\n\",\"$L2c\",\"\\n\",\"$L2d\",\"\\n\",\"$L2e\",\"\\n\",\"$L2f\",\"\\n\",\"$L30\",\"\\n\",\"$L31\",\"\\n\",\"$L32\",\"\\n\",\"$L33\",\"\\n\",\"$L34\",\"\\n\",\"$L35\",\"\\n\",\"$L36\",\"\\n\",\"$L37\",\"\\n\",\"$L38\",\"\\n\",\"$L39\",\"\\n\",\"$L3a\",\"\\n\",\"$L3b\",\"\\n\",\"$L3c\",\"\\n\",\"$L3d\",\"\\n\",\"$L3e\",\"\\n\",\"$L3f\",\"\\n\",\"$L40\",\"\\n\",\"$L41\",\"\\n\",\"$L42\",\"\\n\",\"$L43\",\"\\n\",\"$L44\",\"\\n\",\"$L45\",\"\\n\",\"$L46\",\"\\n\",\"$L47\",\"\\n\",\"$L48\",\"\\n\",\"$L49\",\"\\n\",\"$L4a\",\"\\n\",\"$L4b\",\"\\n\",\"$L4c\",\"\\n\",\"$L4d\",\"\\n\",\"$L4e\",\"\\n\",\"$L4f\",\"\\n\",\"$L50\",\"\\n\",\"$L51\",\"\\n\",\"$L52\",\"\\n\",\"$L53\",\"\\n\",\"$L54\",\"\\n\",\"$L55\",\"\\n\",\"$L56\",\"\\n\",\"$L57\",\"\\n\",\"$L58\",\"\\n\",\"$L59\",\"\\n\",\"$L5a\",\"\\n\",\"$L5b\",\"\\n\",\"$L5c\",\"\\n\",\"$L5d\",\"\\n\",\"$L5e\",\"\\n\",\"$L5f\",\"\\n\",\"$L60\",\"\\n\",\"$L61\",\"\\n\",\"$L62\",\"\\n\",\"$L63\",\"\\n\",\"$L64\",\"\\n\",\"$L65\",\"\\n\",\"$L66\",\"\\n\",\"$L67\",\"\\n\",\"$L68\",\"\\n\",\"$L69\",\"\\n\",\"$L6a\",\"\\n\",\"$L6b\",\"\\n\",\"$L6c\",\"\\n\",\"$L6d\",\"\\n\",\"$L6e\",\"\\n\",\"$L6f\",\"\\n\",\"$L70\",\"\\n\",\"$L71\",\"\\n\",\"$L72\",\"\\n\",\"$L73\",\"\\n\",\"$L74\",\"\\n\",\"$L75\",\"\\n\",\"$L76\",\"\\n\",\"$L77\",\"\\n\",\"$L78\",\"\\n\",\"$L79\",\"\\n\",\"$L7a\",\"\\n\",\"$L7b\",\"\\n\",\"$L7c\",\"\\n\",\"$L7d\",\"\\n\",\"$L7e\",\"\\n\",\"$L7f\",\"\\n\",\"$L80\",\"\\n\",\"$L81\"]}]]}]\n"])</script><script>self.__next_f.push([1,"84:I[51504,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"CodeBlock\"]\n85:I[51504,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"Pre\"]\n10:[\"$\",\"p\",null,{\"children\":\"User\"}]\n11:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n12:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n13:[\"$\",\"p\",null,{\"children\":\"Yes, the speaker is female and in her twenties.\"}]\n14:[\"$\",\"p\",null,{\"children\":\"User\"}]\n15:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n16:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n82:T452,I'm sorry to hear that you're feeling stressed about your exam. It's completely normal to feel anxious when you're preparing for an important test. Here are some tips that might help you: 1. Start studying early: Don't leave everything until the last minute. Break up your study sessions into smaller chunks of time, and try to stick to a regular schedule. 2. Find a quiet place to study: A quiet environment can help you concentrate better. If possible, find a library or a study room where you can work without distractions. 3.Take breaks: It's important to take breaks during your study sessions. This will give your brain a chance to rest and recharge. Try taking short breaks every hour or so. 4. Get enough sleep: Lack of sleep can make it harder to focus and retain information. Make sure you're getting enough sleep each night, ideally around 7-8 hours. 5. Practice relaxation techniques: Deep breathing exercises, meditation, or yoga can all help you relax and reduce stress. Remember, it's okay if you're not feeling well-prepared. Just do your best, and trust yourself. Good luck with your exam!17:[\"$\",\"p\",null,{\"children\":\"$82\"}]\n18:[\"$\",\"p\",null,{\"children\":\"Voice Chat: Speech translation Next\"}]\n19:[\"$\",\"p\",null,{\"children\":\"User\"}]\n1a:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n1b:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n1c:[\"$\",\"p\",null,{\"children\":\"每个人都希望被欣赏,所以如果你欣赏某人,不要把它保密。\"}]\n1d:[\"$\",\"p\",null,{\"children\":\"User\"}]\n1e:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n1f:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n20:[\"$\",\"p\",null,{\"children\":\"Jeder möchte geschätzt werden, also wenn du jemanden schätzt, lass es nicht als Geheimnis verbergen.\"}]\n21:[\"$\",\"p\",null,{\"children\":\"User\"}]\n22:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n23:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n24:[\"$\",\"p\",null,{\"children\":\"Chacun veut être apprecié, alors si tu apprécies quelqu'un, ne le gardes pas secret.\"}]\n25:[\"$\",\"p\",null,{\"children\":\"User\"}]\n26:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n27:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n28:[\"$\",\"p\",null,{\"children\":\"1. 每个人都喜欢被赞美,所以如果你喜欢一个人,不要隐藏你的赞赏。 2. 所有人都渴望得到认可,因此如果你欣赏某人,请不要独自享用这种感觉。 3. 人们都希望被欣赏,所以如果你喜欢某人,不要独自保密欣赏他人是一种美德,所以不要让别人知道你对他们的赞赏是秘密的。 4. 人们都希望受到赞扬,所以如果你欣赏某人,不妨公开表达出来。 5. 如果你喜欢某人,不要犹豫告诉他们,因为每个人都有权利享受他人的赞赏。\"}]\n29:[\"$\",\"p\",null,{\"children\":\"Voice Chat: Detecting background noise and responding accordingly Next\"}]\n2a:[\"$\",\"p\",null,{\"children\":\"User\"}]\n2b:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n2c:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n2d:[\"$\",\"p\",null,{\"children\":\"Use headphones to block out external noise and find a quiet place to stu"])</script><script>self.__next_f.push([1,"dy. Prioritize your tasks and set realistic goals for yourself. Use active learning techniques such as summarizing, note-taking, and quizzing to help you retain information. Take breaks and practice self-care to avoid burnout.\"}]\n2e:[\"$\",\"p\",null,{\"children\":\"User\"}]\n2f:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n30:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n31:[\"$\",\"p\",null,{\"children\":\"Yes, you can try negotiating with them to reach a mutually beneficial agreement. You could also consider seeking help from a mediator or professional negotiator if needed.\"}]\n32:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"audio-analysis\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#audio-analysis\",\"className\":\"peer\",\"children\":\"Audio Analysis\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n33:[\"$\",\"p\",null,{\"children\":\"Audio Analysis : Speech transcription and story telling Next\"}]\n34:[\"$\",\"p\",null,{\"children\":\"User\"}]\n35:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n36:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n37:[\"$\",\"p\",null,{\"children\":\"The original content of this audio is: 'Stop all the clocks, cut off the telephone, prevent the dog from barking, silence the pianos and with muffled drum bring out the coffin, let the mourners come.'\"}]\n38:[\"$\",\"p\",null,{\"children\":\"User\"}]\n39:[\"$\",\"p\",null,{\"children\":\"No less than 50 words and no more than 200 words, add scenes such as rain and thunder to the poem. Finally, give the verses you created in lines.\"}]\n3a:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n3b:[\"$\",\"p\",null,{\"children\":\"In the midst of an eerie stormy night, With raindrops falling heavy and bright, The world seemed to hush its voice, As winds howled through the darkened space. Stop all the clocks, the time stood still, As the lightning flashed through the sky, The telephone's ring was drowned out, By the roaring thunder that shook the ground. Prevent the dog from barking, its cries were silenced, By the fear that gripped it in the night, Silence the pianos, their keys were muted, As the mournful sound of raindrops beat on wood. With muffled drums, a slow march began, A solemn procession through the storm, The coffin was carried, heavy and solemn, Let the mourners come, to pay their final respects. As the storm slowly passed, the world emerged, A new day dawned, but memories lingered, Of the night when time stood still, And the mourners came, to say goodbye.\"}]\n3c:[\"$\",\"p\",null,{\"children\":\"Audio Analysis: Sound analysis Next\"}]\n3d:[\"$\",\"p\",null,{\"children\":\"User\"}]\n3e:[\"$\",\"p\",null,{\"children\":\"What do you hear? Your browser does not support the audio element.\"}]\n3f:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n40:[\"$\",\"p\",null,{\"children\":\"I heard the sound of an alarm and a truck's air brake mixed with the noise of a heavy engine running and shifting gears.\"}]\n41:[\"$\",\"p\",null,{\"children\":\"User\"}]\n42:[\"$\",\"p\",null,{\"children\":\"Under what circumstances can you hear such sounds?\"}]\n43:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n44:[\"$\",\"p\",null,{\"children\":\"These types of sounds might be commonly heard in industrial settings like construction sites or factories where machinery is operated, or during emergency situations like traffic accidents where sirens are triggered.\"}]\n45:[\"$\",\"p\",null,{\"children\":\"User\"}]\n46:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n47:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n83:T455,It's understandable to feel scared under any situation that makes you feel"])</script><script>self.__next_f.push([1," uncomfortable. It's important to remember that it's okay to be scared. Here are some things you can do: 1. Take deep breaths: Inhale deeply through your nose and exhale slowly through your mouth. This can help calm your mind and body. 2. Find a safe place: If possible, move to a safe location away from the source of the fear. If you're in a car, pull over to a parking lot or a safe spot on the side of the road. 3. Stay informed: If you have access to information about the situation, stay informed but don't overdo it. Too much information can create more anxiety. 4. Talk to someone: Talking to someone you trust can help you process your feelings and gain perspective. You can call a friend, family member, or even a professional counselor if needed. 5. Practice relaxation techniques: Listening to music, doing yoga or meditation, or engaging in other relaxing activities can help reduce stress and anxiety. Remember, it's okay to take time for yourself to process your emotions and come up with a plan that works best for you.48:[\"$\",\"p\",null,{\"children\":\"$83\"}]\n49:[\"$\",\"p\",null,{\"children\":\"Audio Analysis: Music analysis Next\"}]\n4a:[\"$\",\"p\",null,{\"children\":\"User\"}]\n4b:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n4c:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n4d:[\"$\",\"p\",null,{\"children\":\"This is a pop punk music piece. There is a male vocalist singing melodically in the lead. The tune is being played by the guitar with the bass guitar playing in the background. The rhythmic background consists of loud and aggressive sounding drums. The atmosphere is rebellious. This piece could be used in the soundtrack of a high school drama movie or TV show during scenes where the characters are rebelling against authority.\"}]\n4e:[\"$\",\"p\",null,{\"children\":\"User\"}]\n4f:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n50:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n51:[\"$\",\"p\",null,{\"children\":\"The key of this music is F# major.\"}]\n52:[\"$\",\"p\",null,{\"children\":\"User\"}]\n53:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n54:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n55:[\"$\",\"p\",null,{\"children\":\"The tempo of this music is 104.17 bpm.\"}]\n56:[\"$\",\"p\",null,{\"children\":\"User\"}]\n57:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n58:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n59:[\"$\",\"p\",null,{\"children\":\"The time signature of this music is 4/4.\"}]\n5a:[\"$\",\"p\",null,{\"children\":\"Audio Analysis: Robustness of mixed audio analysis Next\"}]\n5b:[\"$\",\"p\",null,{\"children\":\"User\"}]\n5c:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n5d:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n5e:[\"$\",\"p\",null,{\"children\":\"The old man laid down his hand to light a cigar.\"}]\n5f:[\"$\",\"p\",null,{\"children\":\"User\"}]\n60:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n61:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n62:[\"$\",\"p\",null,{\"children\":\"The old man laid down his hand to light a cigar.\"}]\n63:[\"$\",\"p\",null,{\"children\":\"User\"}]\n64:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n65:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n66:[\"$\",\"p\",null,{\"children\":\"The old man laid down his hand to light a cigar.\"}]\n67:[\"$\",\"p\",null,{\"children\":\"User\"}]\n68:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n69:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n6a:[\"$\",\"p\",null,{\"children\":\"The old man laid down his hand to light a cigar.\"}]\n6b:[\"$\",\"p\",null,{\"children\":\"User\"}]\n6c:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n6d:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n6e:[\"$\",\"p\",null,{\"children\":\"The lyrics of the singing are 'Waiting for my favorite song.'\"}]\n6f:[\"$\",\"p\",null,{\"children\":\"User\"}]\n70:[\"$\",\"p\",null,{\"children\":\"Your browser does not support the audio element.\"}]\n71:[\"$\",\"p\",null,{\"children\":\"zen-Audio\"}]\n72:[\"$\",\"p\",null,{\"children\":\"The lyrics of the singing are 'Waiting for my favorite song.'\"}]\n73:[\"$\",\"h2\",null,{\"className\":\"flex scro"])</script><script>self.__next_f.push([1,"ll-m-28 flex-row items-center gap-2\",\"id\":\"performance\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#performance\",\"className\":\"peer\",\"children\":\"Performance\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n74:[\"$\",\"p\",null,{\"children\":\"We have conducted a series of experiments on benchmark datasets, including LibriSpeech, Common Voice 15, Fleurs, Aishell2, CoVoST2, Meld, Vocalsound, and AIR-Benchmark, to evaluate the performance of zen-Audio in comparison with our previously released Qwen-Audio as well as the state-of-the-art models in each tasks. Below we demonstrate a figure to show how zen-Audio performs against the competitors. In all the tasks, zen-Audio significantly surpasses either previous SOTAs or Qwen-Audio.\"}]\n75:[\"$\",\"p\",null,{\"children\":\"More specific results on the datasets are listed below in the table.\"}]\n76:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"architecture\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#architecture\",\"className\":\"peer\",\"children\":\"Architecture\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n77:[\"$\",\"p\",null,{\"children\":\"Below is a demonstration of the training architecture. Specifically, we start from the Qwen language model and an audio encoder as the foundation models. We sequentially apply multi-task pretraining for the audio language alignment, and supervised finetuning as well as direct preference optimization to grasp the capabilities of downstream tasks and model human preference.\"}]\n78:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"how-to-use\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#how-to-use\",\"className\":\"peer\",\"children\":\"How to Use\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n79:[\"$\",\"p\",null,{\"children\":[\"Now zen-Audio is officially supported by Hugging Face Transfomers. We advise you install the latest version of \",[\"$\",\"code\",null,{\"children\":\"transformers\"}],\" from source:\"]}]\n7a:[\"$\",\"$L84\",null,{\"className\":\"shiki shiki-themes github-light github-dark\",\"style\":{\"--shiki-light\":\"#24292e\",\"--shiki-dark\":\"#e1e4e8\",\"--shiki-light-bg\":\"#fff\",\"--shiki-dark-bg\":\"#24292e\"},\"tabIndex\":\"0\",\"icon\":\"\u003csvg viewBox=\\\"0 0 24 24\\\"\u003e\u003cpath d=\\\"m 4,4 a 1,1 0 0 0 -0.7070312,0.2929687 1,1 0 0 0 0,1.4140625 L 8.5859375,11 3.2929688,16.292969 a 1,1 0 0 0 0,1.414062 1,1 0 0 0 1.4140624,0 l 5.9999998,-6 a 1.0001,1.0001 0 0 0 0,-1.414062 L 4.7070312,4.2929687 A 1,1 0 0 0 4,4 Z m 8,14 a 1,1 0 0 0 -1,1 1,1 0 0 0 1,1 h 8 a 1,1"])</script><script>self.__next_f.push([1," 0 0 0 1,-1 1,1 0 0 0 -1,-1 z\\\" fill=\\\"currentColor\\\" /\u003e\u003c/svg\u003e\",\"children\":[\"$\",\"$L85\",null,{\"children\":[\"$\",\"code\",null,{\"children\":[[\"$\",\"span\",null,{\"className\":\"line\"}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#6F42C1\",\"--shiki-dark\":\"#B392F0\"},\"children\":\" pip\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" install\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" git+https://github.com/huggingface/transformers\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]]}]}]}]\n7b:[\"$\",\"p\",null,{\"children\":[\"We demonstrate how to use \",[\"$\",\"code\",null,{\"children\":\"zen-Audio-7B-Instruct\"}],\" to play with voice chat and audio analysis. Here is an example of voice chat:\"]}]\n86:T5c0,"])</script><script>self.__next_f.push([1,"\u003csvg viewBox=\"0 0 24 24\"\u003e\u003cpath d=\"M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z\" fill=\"currentColor\" /\u003e\u003c/svg\u003e"])</script><script>self.__next_f.push([1,"7c:[\"$\",\"$L84\",null,{\"className\":\"shiki shiki-themes github-light github-dark\",\"style\":{\"--shiki-light\":\"#24292e\",\"--shiki-dark\":\"#e1e4e8\",\"--shiki-light-bg\":\"#fff\",\"--shiki-dark-bg\":\"#24292e\"},\"tabIndex\":\"0\",\"icon\":\"$86\",\"children\":[\"$\",\"$L85\",null,{\"children\":[\"$\",\"code\",null,{\"children\":[[\"$\",\"span\",null,{\"className\":\"line\"}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" from\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" io \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" BytesIO\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" from\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" urllib.request \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" urlopen\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" librosa\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" from\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" transformers \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" zenAudioForConditionalGeneration, AutoProcessor\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" AutoProcessor.from_pretrained(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"Qwen/zen-Audio-7B-Instruct\\\"\"}],\"$L87\"]}],\"\\n\",\"$L88\",\"\\n\",\"$L89\",\"\\n\",\"$L8a\",\"\\n\",\"$L8b\",\"\\n\",\"$L8c\",\"\\n\",\"$L8d\",\"\\n\",\"$L8e\",\"\\n\",\"$L8f\",\"\\n\",\"$L90\",\"\\n\",\"$L91\",\"\\n\",\"$L92\",\"\\n\",\"$L93\",\"\\n\",\"$L94\",\"\\n\",\"$L95\",\"\\n\",\"$L96\",\"\\n\",\"$L97\",\"\\n\",\"$L98\",\"\\n\",\"$L99\",\"\\n\",\"$L9a\",\"\\n\",\"$L9b\",\"\\n\",\"$L9c\",\"\\n\",\"$L9d\",\"\\n\",\"$L9e\",\"\\n\",\"$L9f\",\"\\n\",\"$La0\",\"\\n\",\"$La1\",\"\\n\",\"$La2\",\"\\n\",\"$La3\",\"\\n\",\"$La4\",\"\\n\",\"$La5\"]}]}]}]\n"])</script><script>self.__next_f.push([1,"7d:[\"$\",\"p\",null,{\"children\":\"In voice chat mode, the user input is simply the audio without text, and the instructions from the users are inside the audio. Next is an example of audio analysis:\"}]\na6:T5c0,"])</script><script>self.__next_f.push([1,"\u003csvg viewBox=\"0 0 24 24\"\u003e\u003cpath d=\"M14.25.18l.9.2.73.26.59.3.45.32.34.34.25.34.16.33.1.3.04.26.02.2-.01.13V8.5l-.05.63-.13.55-.21.46-.26.38-.3.31-.33.25-.35.19-.35.14-.33.1-.3.07-.26.04-.21.02H8.77l-.69.05-.59.14-.5.22-.41.27-.33.32-.27.35-.2.36-.15.37-.1.35-.07.32-.04.27-.02.21v3.06H3.17l-.21-.03-.28-.07-.32-.12-.35-.18-.36-.26-.36-.36-.35-.46-.32-.59-.28-.73-.21-.88-.14-1.05-.05-1.23.06-1.22.16-1.04.24-.87.32-.71.36-.57.4-.44.42-.33.42-.24.4-.16.36-.1.32-.05.24-.01h.16l.06.01h8.16v-.83H6.18l-.01-2.75-.02-.37.05-.34.11-.31.17-.28.25-.26.31-.23.38-.2.44-.18.51-.15.58-.12.64-.1.71-.06.77-.04.84-.02 1.27.05zm-6.3 1.98l-.23.33-.08.41.08.41.23.34.33.22.41.09.41-.09.33-.22.23-.34.08-.41-.08-.41-.23-.33-.33-.22-.41-.09-.41.09zm13.09 3.95l.28.06.32.12.35.18.36.27.36.35.35.47.32.59.28.73.21.88.14 1.04.05 1.23-.06 1.23-.16 1.04-.24.86-.32.71-.36.57-.4.45-.42.33-.42.24-.4.16-.36.09-.32.05-.24.02-.16-.01h-8.22v.82h5.84l.01 2.76.02.36-.05.34-.11.31-.17.29-.25.25-.31.24-.38.2-.44.17-.51.15-.58.13-.64.09-.71.07-.77.04-.84.01-1.27-.04-1.07-.14-.9-.2-.73-.25-.59-.3-.45-.33-.34-.34-.25-.34-.16-.33-.1-.3-.04-.25-.02-.2.01-.13v-5.34l.05-.64.13-.54.21-.46.26-.38.3-.32.33-.24.35-.2.35-.14.33-.1.3-.06.26-.04.21-.02.13-.01h5.84l.69-.05.59-.14.5-.21.41-.28.33-.32.27-.35.2-.36.15-.36.1-.35.07-.32.04-.28.02-.21V6.07h2.09l.14.01zm-6.47 14.25l-.23.33-.08.41.08.41.23.33.33.23.41.08.41-.08.33-.23.23-.33.08-.41-.08-.41-.23-.33-.33-.23-.41-.08-.41.08z\" fill=\"currentColor\" /\u003e\u003c/svg\u003e"])</script><script>self.__next_f.push([1,"7e:[\"$\",\"$L84\",null,{\"className\":\"shiki shiki-themes github-light github-dark\",\"style\":{\"--shiki-light\":\"#24292e\",\"--shiki-dark\":\"#e1e4e8\",\"--shiki-light-bg\":\"#fff\",\"--shiki-dark-bg\":\"#24292e\"},\"tabIndex\":\"0\",\"icon\":\"$a6\",\"children\":[\"$\",\"$L85\",null,{\"children\":[\"$\",\"code\",null,{\"children\":[[\"$\",\"span\",null,{\"className\":\"line\"}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" from\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" io \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" BytesIO\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" from\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" urllib.request \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" urlopen\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" librosa\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" from\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" transformers \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"import\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" zenAudioForConditionalGeneration, AutoProcessor\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" AutoProcessor.from_pretrained(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"Qwen/zen-Audio-7B-Instruct\\\"\"}],\"$La7\"]}],\"\\n\",\"$La8\",\"\\n\",\"$La9\",\"\\n\",\"$Laa\",\"\\n\",\"$Lab\",\"\\n\",\"$Lac\",\"\\n\",\"$Lad\",\"\\n\",\"$Lae\",\"\\n\",\"$Laf\",\"\\n\",\"$Lb0\",\"\\n\",\"$Lb1\",\"\\n\",\"$Lb2\",\"\\n\",\"$Lb3\",\"\\n\",\"$Lb4\",\"\\n\",\"$Lb5\",\"\\n\",\"$Lb6\",\"\\n\",\"$Lb7\",\"\\n\",\"$Lb8\",\"\\n\",\"$Lb9\",\"\\n\",\"$Lba\",\"\\n\",\"$Lbb\",\"\\n\",\"$Lbc\",\"\\n\",\"$Lbd\",\"\\n\",\"$Lbe\",\"\\n\",\"$Lbf\",\"\\n\",\"$Lc0\",\"\\n\",\"$Lc1\",\"\\n\",\"$Lc2\",\"\\n\",\"$Lc3\",\"\\n\",\"$Lc4\",\"\\n\",\"$Lc5\",\"\\n\",\"$Lc6\",\"\\n\",\"$Lc7\",\"\\n\",\"$Lc8\",\"\\n\",\"$Lc9\",\"\\n\",\"$Lca\",\"\\n\",\"$Lcb\",\"\\n\",\"$Lcc\",\"\\n\",\"$Lcd\"]}]}]}]\n"])</script><script>self.__next_f.push([1,"7f:[\"$\",\"p\",null,{\"children\":\"In comparison, in audio analysis mode, there is additional text instructions. However, switching between either mode only needs to modify your user inputs and there is no need to worry about others such as system prompt.\"}]\n80:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"next-step\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#next-step\",\"className\":\"peer\",\"children\":\"Next Step\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n81:[\"$\",\"p\",null,{\"children\":\"This time we bring a new audio language model, zen-Audio, which supports voice chat and audio analysis at the same time and understands more than 8 languages and dialects. In the near future, we plan to train improved zen-Audio models on larger pretraining datasets, enabling the model to support longer audio (over 30s). We also plan to build larger zen-Audio models to explore the scaling laws of audio language models.\"}]\n"])</script><script>self.__next_f.push([1,"87:[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]\n88:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" model \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" zenAudioForConditionalGeneration.from_pretrained(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"Qwen/zen-Audio-7B-Instruct\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"device_map\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"auto\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\n89:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\n8a:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" conversation \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" [\"}]]}]\n8b:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"user\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": [\"}]]}]\n8c:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio_url\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/guess_age_gender.wav\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\n8d:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]},\"}]}]\n8e:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"assistant\\\"\"}],[\"$\",\"span\",null,{\"style\":{"])</script><script>self.__next_f.push([1,"\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"Yes, the speaker is female and in her twenties.\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\n8f:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"user\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": [\"}]]}]\n90:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio_url\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/translate_to_chinese.wav\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\n91:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]},\"}]}]\n92:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]\"}]}]\n93:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" text \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor.apply_chat_template(conversation, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"add_generation_prompt\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"True\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"tokenize\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"False\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\n94:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" audios \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\""])</script><script>self.__next_f.push([1,"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" []\"}]]}]\n95:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" for\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" message \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"in\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" conversation:\"}]]}]\n96:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" if\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\" isinstance\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"(message[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"], \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"list\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"):\"}]]}]\n97:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" for\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ele \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"in\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" message[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]:\"}]]}]\n98:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" if\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ele[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"] \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"==\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" \\\"audio\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\":\"}]]}]\n99:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" audios.append(librosa.load(\"}]}]\n9a:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" BytesIO(urlopen(ele[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"'audio_url'\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]).read()), \"}]]}]\n9b:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\" sr\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"processor.feature_extractor.sampling_rate)[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"0\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]\"}]]}]\n9c:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dar"])</script><script>self.__next_f.push([1,"k\":\"#E1E4E8\"},\"children\":\" )\"}]}]\n9d:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\n"])</script><script>self.__next_f.push([1,"9e:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" inputs \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"text\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"text, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"audios\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"audios, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"return_tensors\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"pt\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"padding\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"True\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\n"])</script><script>self.__next_f.push([1,"9f:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" inputs.input_ids \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" inputs.input_ids.to(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"cuda\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\na0:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\na1:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" generate_ids \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" model.generate(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"**\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"inputs, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"max_length\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"256\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\na2:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" generate_ids \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" generate_ids[:, inputs.input_ids.size(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"1\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"):]\"}]]}]\na3:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\n"])</script><script>self.__next_f.push([1,"a4:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" response \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor.batch_decode(generate_ids, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"skip_special_tokens\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"True\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"clean_up_tokenization_spaces\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"False\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"0\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]\"}]]}]\n"])</script><script>self.__next_f.push([1,"a5:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\na7:[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]\na8:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" model \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" zenAudioForConditionalGeneration.from_pretrained(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"Qwen/zen-Audio-7B-Instruct\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"device_map\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"auto\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\na9:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\naa:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" conversation \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" [\"}]]}]\nab:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"'role'\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"'system'\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"'content'\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"'You are a helpful assistant.'\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"}, \"}]]}]\nac:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"user\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": [\"}]]}]\nad:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\","])</script><script>self.__next_f.push([1,"\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio_url\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/glass-breaking-151256.mp3\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\nae:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"text\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"text\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"What's that sound?\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\naf:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]},\"}]}]\nb0:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"assistant\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"It is the sound of glass shattering.\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\nb1:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"user\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": [\"}]]}]\nb2:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"text\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"text\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24"])</script><script>self.__next_f.push([1,"292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"What can you do when you hear that?\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\nb3:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]},\"}]}]\nb4:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"assistant\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"Stay alert and cautious, and check if anyone is hurt or if there is any damage to property.\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\nb5:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"role\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"user\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": [\"}]]}]\nb6:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"audio_url\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/zen-Audio/audio/1272-128104-0000.flac\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\nb7:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" {\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"text\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"text\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\": \"}],[\"$\",\"span\",null,{\"style\":"])</script><script>self.__next_f.push([1,"{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"What does the person say?\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"},\"}]]}]\nb8:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]},\"}]}]\nb9:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ]\"}]}]\nba:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" text \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor.apply_chat_template(conversation, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"add_generation_prompt\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"True\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"tokenize\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"False\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\nbb:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" audios \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" []\"}]]}]\nbc:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" for\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" message \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"in\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" conversation:\"}]]}]\nbd:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" if\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\" isinstance\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"(message[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"], \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"list\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"):\"}]]}]\nbe:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\" for\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ele \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"in\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" message[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"content\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]:\"}]]}]\nbf:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F9758"])</script><script>self.__next_f.push([1,"3\"},\"children\":\" if\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" ele[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"type\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"] \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"==\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" \\\"audio\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\":\"}]]}]\nc0:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" audios.append(\"}]}]\nc1:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" librosa.load(\"}]}]\nc2:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" BytesIO(urlopen(ele[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"'audio_url'\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]).read()), \"}]]}]\nc3:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\" sr\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"processor.feature_extractor.sampling_rate)[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"0\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]\"}]]}]\nc4:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" )\"}]}]\nc5:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\n"])</script><script>self.__next_f.push([1,"c6:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" inputs \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"text\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"text, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"audios\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"audios, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"return_tensors\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"pt\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"padding\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"True\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\n"])</script><script>self.__next_f.push([1,"c7:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" inputs.input_ids \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" inputs.input_ids.to(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"cuda\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\nc8:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\nc9:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" generate_ids \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" model.generate(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"**\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"inputs, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"max_length\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"256\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")\"}]]}]\nca:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" generate_ids \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" generate_ids[:, inputs.input_ids.size(\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"1\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"):]\"}]]}]\ncb:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\n"])</script><script>self.__next_f.push([1,"cc:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" response \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" processor.batch_decode(generate_ids, \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"skip_special_tokens\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"True\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\", \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#E36209\",\"--shiki-dark\":\"#FFAB70\"},\"children\":\"clean_up_tokenization_spaces\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#D73A49\",\"--shiki-dark\":\"#F97583\"},\"children\":\"=\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"False\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\")[\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\"0\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"]\"}]]}]\n"])</script><script>self.__next_f.push([1,"cd:[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\" \"}]}]\n"])</script><script>self.__next_f.push([1,"b:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"2\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: dark)\",\"content\":\"#0A0A0A\"}],[\"$\",\"meta\",\"3\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: light)\",\"content\":\"#fff\"}]]\n"])</script><script>self.__next_f.push([1,"9:null\nd:[[\"$\",\"title\",\"0\",{\"children\":\"zen-Audio: Chat with Your Voice! — Zen LM Blog | Zen LM\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD\"}],[\"$\",\"meta\",\"2\",{\"property\":\"og:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"3\",{\"property\":\"og:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}],[\"$\",\"meta\",\"4\",{\"property\":\"og:url\",\"content\":\"https://zenlm.org\"}],[\"$\",\"meta\",\"5\",{\"property\":\"og:site_name\",\"content\":\"Zen LM\"}],[\"$\",\"meta\",\"6\",{\"property\":\"og:type\",\"content\":\"website\"}],[\"$\",\"meta\",\"7\",{\"name\":\"twitter:card\",\"content\":\"summary_large_image\"}],[\"$\",\"meta\",\"8\",{\"name\":\"twitter:site\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"9\",{\"name\":\"twitter:creator\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"10\",{\"name\":\"twitter:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"11\",{\"name\":\"twitter:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}]]\n"])</script><script>
(function(){
// After React renders the lotus emoji from RSC payload, walk the DOM
// and replace it with the enso SVG. Polls so subsequent React re-renders
// also get cleaned up.
function swap(){
// 1. Replace lotus + ' Zen LM' text inside <a> brand links
document.querySelectorAll('a').forEach(function(a){
if (a.dataset.zenLotusSwapped) return;
var t = (a.textContent || '');
if (!/.*Zen LM|Zen LM.*/.test(t)) return;
// Find the lotus text node specifically
var walker = document.createTreeWalker(a, NodeFilter.SHOW_TEXT, null);
var node;
while ((node = walker.nextNode())) {
if (node.nodeValue && node.nodeValue.indexOf('') !== -1) {
node.nodeValue = node.nodeValue.replace(/\s?/g, '');
}
}
// Inject enso SVG at start
if (!a.querySelector('svg[aria-label="Zen LM"]')) {
var ns = 'http://www.w3.org/2000/svg';
var svg = document.createElementNS(ns, 'svg');
svg.setAttribute('viewBox', '0 0 512 512');
svg.setAttribute('fill', 'none');
svg.setAttribute('width', '18');
svg.setAttribute('height', '18');
svg.setAttribute('aria-label', 'Zen LM');
svg.style.cssText = 'display:inline-block;vertical-align:-2px;margin-right:6px;flex-shrink:0';
var p = document.createElementNS(ns, 'path');
p.setAttribute('d', 'M 256 84 A 172 172 0 1 0 256 428 A 172 172 0 1 0 256 84 Z');
p.setAttribute('stroke', 'currentColor');
p.setAttribute('stroke-width', '26');
p.setAttribute('stroke-linecap', 'round');
p.setAttribute('stroke-linejoin', 'round');
svg.appendChild(p);
a.insertBefore(svg, a.firstChild);
}
a.dataset.zenLotusSwapped = '1';
});
}
function start(){ swap(); setInterval(swap, 600); }
if (document.readyState !== 'loading') start();
else document.addEventListener('DOMContentLoaded', start);
})();
</script>
<style id="zenlm-brand-anim">
@keyframes zenlm-brand-draw { to { stroke-dashoffset: 0; } }
svg.zenlm-brand-svg .zenlm-brand-path {
stroke-dasharray: 1100;
stroke-dashoffset: 1100;
animation: zenlm-brand-draw 1.4s cubic-bezier(.45,0,.2,1) 0.1s 1 forwards;
}
.zen-link-icon { display: inline-block; vertical-align: middle; flex-shrink: 0; }
</style></body></html>