1528 lines
98 KiB
HTML
1528 lines
98 KiB
HTML
<!DOCTYPE html>
|
||
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
|
||
|
||
<meta charset="utf-8">
|
||
<meta name="generator" content="quarto-1.8.27">
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
|
||
|
||
|
||
<title>Orpheus – Axolotl</title>
|
||
<style>
|
||
code{white-space: pre-wrap;}
|
||
span.smallcaps{font-variant: small-caps;}
|
||
div.columns{display: flex; gap: min(4vw, 1.5em);}
|
||
div.column{flex: auto; overflow-x: auto;}
|
||
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
|
||
ul.task-list{list-style: none;}
|
||
ul.task-list li input[type="checkbox"] {
|
||
width: 0.8em;
|
||
margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
|
||
vertical-align: middle;
|
||
}
|
||
/* CSS for syntax highlighting */
|
||
html { -webkit-text-size-adjust: 100%; }
|
||
pre > code.sourceCode { white-space: pre; position: relative; }
|
||
pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
|
||
pre > code.sourceCode > span:empty { height: 1.2em; }
|
||
.sourceCode { overflow: visible; }
|
||
code.sourceCode > span { color: inherit; text-decoration: inherit; }
|
||
div.sourceCode { margin: 1em 0; }
|
||
pre.sourceCode { margin: 0; }
|
||
@media screen {
|
||
div.sourceCode { overflow: auto; }
|
||
}
|
||
@media print {
|
||
pre > code.sourceCode { white-space: pre-wrap; }
|
||
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
|
||
}
|
||
pre.numberSource code
|
||
{ counter-reset: source-line 0; }
|
||
pre.numberSource code > span
|
||
{ position: relative; left: -4em; counter-increment: source-line; }
|
||
pre.numberSource code > span > a:first-child::before
|
||
{ content: counter(source-line);
|
||
position: relative; left: -1em; text-align: right; vertical-align: baseline;
|
||
border: none; display: inline-block;
|
||
-webkit-touch-callout: none; -webkit-user-select: none;
|
||
-khtml-user-select: none; -moz-user-select: none;
|
||
-ms-user-select: none; user-select: none;
|
||
padding: 0 4px; width: 4em;
|
||
}
|
||
pre.numberSource { margin-left: 3em; padding-left: 4px; }
|
||
div.sourceCode
|
||
{ }
|
||
@media screen {
|
||
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
|
||
}
|
||
</style>
|
||
|
||
|
||
<script src="../../site_libs/quarto-nav/quarto-nav.js"></script>
|
||
<script src="../../site_libs/clipboard/clipboard.min.js"></script>
|
||
<script src="../../site_libs/quarto-search/autocomplete.umd.js"></script>
|
||
<script src="../../site_libs/quarto-search/fuse.min.js"></script>
|
||
<script src="../../site_libs/quarto-search/quarto-search.js"></script>
|
||
<meta name="quarto:offset" content="../../">
|
||
<link href="../../favicon.jpg" rel="icon" type="image/jpeg">
|
||
<script src="../../site_libs/quarto-html/quarto.js" type="module"></script>
|
||
<script src="../../site_libs/quarto-html/tabsets/tabsets.js" type="module"></script>
|
||
<script src="../../site_libs/quarto-html/axe/axe-check.js" type="module"></script>
|
||
<script src="../../site_libs/quarto-html/popper.min.js"></script>
|
||
<script src="../../site_libs/quarto-html/tippy.umd.min.js"></script>
|
||
<script src="../../site_libs/quarto-html/anchor.min.js"></script>
|
||
<link href="../../site_libs/quarto-html/tippy.css" rel="stylesheet">
|
||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-4d9afe2b8d18ee9fa5d0d57b5ed4214d.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||
<script src="../../site_libs/bootstrap/bootstrap.min.js"></script>
|
||
<link href="../../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
|
||
<link href="../../site_libs/bootstrap/bootstrap-35ef2ff98a2131eb4c49a687ae04ea22.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
|
||
<script id="quarto-search-options" type="application/json">{
|
||
"location": "navbar",
|
||
"copy-button": false,
|
||
"collapse-after": 3,
|
||
"panel-placement": "end",
|
||
"type": "overlay",
|
||
"limit": 50,
|
||
"keyboard-shortcut": [
|
||
"f",
|
||
"/",
|
||
"s"
|
||
],
|
||
"show-item-context": false,
|
||
"language": {
|
||
"search-no-results-text": "No results",
|
||
"search-matching-documents-text": "matching documents",
|
||
"search-copy-link-title": "Copy link to search",
|
||
"search-hide-matches-text": "Hide additional matches",
|
||
"search-more-match-text": "more match in this document",
|
||
"search-more-matches-text": "more matches in this document",
|
||
"search-clear-button-title": "Clear",
|
||
"search-text-placeholder": "",
|
||
"search-detached-cancel-button-title": "Cancel",
|
||
"search-submit-button-title": "Submit",
|
||
"search-label": "Search"
|
||
}
|
||
}</script>
|
||
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-9KYCVJBNMQ"></script>
|
||
|
||
<script type="text/javascript">
|
||
|
||
window.dataLayer = window.dataLayer || [];
|
||
function gtag(){dataLayer.push(arguments);}
|
||
gtag('js', new Date());
|
||
gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||
</script>
|
||
|
||
|
||
<link rel="stylesheet" href="../../styles.css">
|
||
</head>
|
||
|
||
<body class="nav-sidebar docked nav-fixed quarto-light">
|
||
|
||
<div id="quarto-search-results"></div>
|
||
<header id="quarto-header" class="headroom fixed-top">
|
||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||
<div class="navbar-container container-fluid">
|
||
<div class="navbar-brand-container mx-auto">
|
||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo light-content">
|
||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo dark-content">
|
||
</a>
|
||
</div>
|
||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||
<a href="https://twitter.com/axolotl_ai" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-twitter"></i></a>
|
||
<a href="https://github.com/axolotl-ai-cloud/axolotl/" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-github"></i></a>
|
||
<a href="https://discord.gg/7m9sfhzaf3" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-discord"></i></a>
|
||
</div>
|
||
<div id="quarto-search" class="" title="Search"></div>
|
||
</div> <!-- /container-fluid -->
|
||
</nav>
|
||
<nav class="quarto-secondary-nav">
|
||
<div class="container-fluid d-flex">
|
||
<button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
|
||
<i class="bi bi-layout-text-sidebar-reverse"></i>
|
||
</button>
|
||
<nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../../docs/getting-started.html">Getting Started</a></li><li class="breadcrumb-item"><a href="../../docs/models/kimi-linear.html">Model Guides</a></li><li class="breadcrumb-item"><a href="../../docs/models/orpheus.html">Orpheus</a></li></ol></nav>
|
||
<a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
|
||
</a>
|
||
</div>
|
||
</nav>
|
||
</header>
|
||
<!-- content -->
|
||
<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article page-navbar">
|
||
<!-- sidebar -->
|
||
<nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
|
||
<div class="sidebar-menu-container">
|
||
<ul class="list-unstyled mt-1">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../index.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Home</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Getting Started</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/getting-started.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quickstart</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/installation.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Installation</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/inference.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Inference and Merging</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Model Guides</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth2 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/kimi-linear.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Kimi Linear</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/plano.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Plano Orchestrator</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/mimo.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">MiMo</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/internvl3_5.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">InternVL 3.5</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/olmo3.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">OLMo 3</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/trinity.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Trinity</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/arcee.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Arcee AFM</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="false">
|
||
<span class="menu-text">Ministral3</span></a>
|
||
<a class="sidebar-item-toggle text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="false" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth3 ">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/ministral3.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Ministral3</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/ministral3/think.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Ministral 3 Thinking</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/ministral3/vision.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Ministral 3 Vision</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="false">
|
||
<span class="menu-text">Magistral</span></a>
|
||
<a class="sidebar-item-toggle text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="false" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-4" class="collapse list-unstyled sidebar-section depth3 ">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/magistral.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Magistral</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/magistral/think.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Magistral Thinking</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/magistral/vision.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Magistral Vision</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/ministral.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Ministral</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/mistral-small.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Mistral Small 3.1/3.2</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/voxtral.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Voxtral</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/devstral.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Devstral</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/mistral.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Mistral 7B</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/llama-4.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Llama 4</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/llama-2.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Llama 2</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/qwen3-next.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Qwen 3 Next</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/qwen3.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Qwen 3</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/gemma3n.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Gemma 3n</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/apertus.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Apertus</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/gpt-oss.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">GPT-OSS</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/seed-oss.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Seed-OSS</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/phi.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Phi</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/smolvlm2.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">SmolVLM 2</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/granite4.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Granite 4</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/LiquidAI.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Liquid Foundation Models 2</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/hunyuan.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Hunyuan</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/jamba.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Jamba</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/models/orpheus.html" class="sidebar-item-text sidebar-link active">
|
||
<span class="menu-text">Orpheus</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Command Line Interface (CLI)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/telemetry.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Telemetry</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/config-reference.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Config Reference</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/api" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">API Reference</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/index.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Formats</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-5" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-5" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/pretraining.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Pre-training</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/inst_tune.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Instruction Tuning</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/conversation.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Conversation</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/stepwise_supervised.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Stepwise Supervised Format</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/template_free.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Template-Free</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset-formats/tokenized.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Custom Pre-Tokenized Dataset</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Deployments</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-6" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/docker.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Docker</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/multi-gpu.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Multi-GPU</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/multi-node.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Multi Node</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/ray-integration.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Ray Train</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">AMD GPUs on HPC Systems</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/mac.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Mac M-series</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">How To Guides</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-7" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/multimodal.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">MultiModal / Vision Language Models (BETA)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/rlhf.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">RLHF (Beta)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/reward_modelling.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Reward Modelling</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/lr_groups.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Learning Rate Groups</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/lora_optims.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">LoRA Optimizations</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset_loading.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Loading</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/qat.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quantization Aware Training (QAT)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/quantize.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quantization with torchao</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/optimizations.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Optimizations Guide</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-8" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Core Concepts</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-8" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-8" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/batch_vs_grad.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Batch size vs Gradient accumulation</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset_preprocessing.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Preprocessing</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/streaming.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Streaming Datasets</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/multipack.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Multipack (Sample Packing)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/mixed_precision.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Mixed Precision Training</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/optimizers.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Optimizers</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/attention.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Attention</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-9" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Advanced Features</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-9" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-9" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">FSDP + QLoRA</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/unsloth.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Unsloth</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/torchao.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">PyTorch ao</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/custom_integrations.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Custom Integrations</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/sequence_parallelism.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Sequence Parallelism</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/gradient_checkpointing.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Gradient Checkpointing and Activation Offloading</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/nd_parallelism.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">N-D Parallelism (Beta)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/expert_quantization.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">MoE Expert Quantization</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-10" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Troubleshooting</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-10" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-10" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/faq.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">FAQ</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/debugging.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Debugging</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/nccl.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">NCCL</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</nav>
|
||
<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
|
||
<!-- margin-sidebar -->
|
||
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
|
||
<nav id="TOC" role="doc-toc" class="toc-active">
|
||
<h2 id="toc-title">On this page</h2>
|
||
|
||
<ul>
|
||
<li><a href="#dataset-pre-processing-for-pre-training" id="toc-dataset-pre-processing-for-pre-training" class="nav-link active" data-scroll-target="#dataset-pre-processing-for-pre-training">Dataset pre-processing for pre-training</a></li>
|
||
<li><a href="#finetune-pre-processing" id="toc-finetune-pre-processing" class="nav-link" data-scroll-target="#finetune-pre-processing">Finetune pre-processing</a></li>
|
||
<li><a href="#training" id="toc-training" class="nav-link" data-scroll-target="#training">Training</a></li>
|
||
<li><a href="#inference" id="toc-inference" class="nav-link" data-scroll-target="#inference">Inference</a></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
<!-- main -->
|
||
<main class="content" id="quarto-document-content">
|
||
|
||
<header id="title-block-header" class="quarto-title-block default"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../../docs/getting-started.html">Getting Started</a></li><li class="breadcrumb-item"><a href="../../docs/models/kimi-linear.html">Model Guides</a></li><li class="breadcrumb-item"><a href="../../docs/models/orpheus.html">Orpheus</a></li></ol></nav>
|
||
<div class="quarto-title">
|
||
<h1 class="title">Orpheus</h1>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="quarto-title-meta">
|
||
|
||
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</header>
|
||
|
||
|
||
<p>In this example, we finetune Orpcanopylabs/orpheus-tts-0.1-pretrained (a LLaMA 3.2 3b model) to output audio.</p>
|
||
<p>The <code>finetune.yml</code> withe current settings will run on any Nvidia GPU with 45GB VRAM or more. If you adjust the batch size it can easily run on any GPU under 24GB.</p>
|
||
<section id="dataset-pre-processing-for-pre-training" class="level2">
|
||
<h2 class="anchored" data-anchor-id="dataset-pre-processing-for-pre-training">Dataset pre-processing for pre-training</h2>
|
||
<p>If you are adding another voice in English, please jump ahead to finetuning pre-processing.</p>
|
||
<p>For this to work, we need to preprocess our dataset. Since we are expecting to output audio, we will need to add tokens to the tokenizer.</p>
|
||
<p>Using this code, it will download the SNAC model and add the correct tokens and upload the final dataset.</p>
|
||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> torch</span>
|
||
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> snac <span class="im">import</span> SNAC</span>
|
||
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> datasets <span class="im">import</span> load_dataset</span>
|
||
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> huggingface_hub <span class="im">import</span> snapshot_download</span>
|
||
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> datasets <span class="im">import</span> load_dataset</span>
|
||
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> random</span>
|
||
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> torchaudio.transforms <span class="im">as</span> T</span>
|
||
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> transformers <span class="im">import</span> AutoTokenizer</span>
|
||
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> os</span>
|
||
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>my_original_dataset_name <span class="op">=</span> <span class="st">"<huggingface-id-of-dataset-that-we-want-to-preprocess>"</span></span>
|
||
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a>name_to_push_dataset_to <span class="op">=</span> <span class="st">"<huggingface-id-of-where-to-save-dataset>"</span></span>
|
||
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a>dsn <span class="op">=</span> my_original_dataset_name</span>
|
||
<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a>snapshot_download(</span>
|
||
<span id="cb1-17"><a href="#cb1-17" aria-hidden="true" tabindex="-1"></a> repo_id<span class="op">=</span>dsn,</span>
|
||
<span id="cb1-18"><a href="#cb1-18" aria-hidden="true" tabindex="-1"></a> repo_type<span class="op">=</span><span class="st">"dataset"</span>,</span>
|
||
<span id="cb1-19"><a href="#cb1-19" aria-hidden="true" tabindex="-1"></a> revision<span class="op">=</span><span class="st">"main"</span>,</span>
|
||
<span id="cb1-20"><a href="#cb1-20" aria-hidden="true" tabindex="-1"></a> max_workers<span class="op">=</span><span class="dv">64</span>,</span>
|
||
<span id="cb1-21"><a href="#cb1-21" aria-hidden="true" tabindex="-1"></a>)</span>
|
||
<span id="cb1-22"><a href="#cb1-22" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-23"><a href="#cb1-23" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-24"><a href="#cb1-24" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(dsn, split<span class="op">=</span><span class="st">"train"</span>)</span>
|
||
<span id="cb1-25"><a href="#cb1-25" aria-hidden="true" tabindex="-1"></a>ds_sample_rate <span class="op">=</span> ds[<span class="dv">0</span>][<span class="st">"audio"</span>][<span class="st">"sampling_rate"</span>]</span>
|
||
<span id="cb1-26"><a href="#cb1-26" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-27"><a href="#cb1-27" aria-hidden="true" tabindex="-1"></a>model <span class="op">=</span> SNAC.from_pretrained(<span class="st">"hubertsiuzdak/snac_24khz"</span>)</span>
|
||
<span id="cb1-28"><a href="#cb1-28" aria-hidden="true" tabindex="-1"></a>model <span class="op">=</span> model.to(<span class="st">"mps"</span>)</span>
|
||
<span id="cb1-29"><a href="#cb1-29" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-30"><a href="#cb1-30" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> tokenise_audio(waveform):</span>
|
||
<span id="cb1-31"><a href="#cb1-31" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> torch.from_numpy(waveform).unsqueeze(<span class="dv">0</span>)</span>
|
||
<span id="cb1-32"><a href="#cb1-32" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> waveform.to(dtype<span class="op">=</span>torch.float32)</span>
|
||
<span id="cb1-33"><a href="#cb1-33" aria-hidden="true" tabindex="-1"></a> resample_transform <span class="op">=</span> T.Resample(orig_freq<span class="op">=</span>ds_sample_rate, new_freq<span class="op">=</span><span class="dv">24000</span>)</span>
|
||
<span id="cb1-34"><a href="#cb1-34" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> resample_transform(waveform)</span>
|
||
<span id="cb1-35"><a href="#cb1-35" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-36"><a href="#cb1-36" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> waveform.unsqueeze(<span class="dv">0</span>).to(<span class="st">"cuda"</span>)</span>
|
||
<span id="cb1-37"><a href="#cb1-37" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-38"><a href="#cb1-38" aria-hidden="true" tabindex="-1"></a> <span class="co">#generate the codes from snac</span></span>
|
||
<span id="cb1-39"><a href="#cb1-39" aria-hidden="true" tabindex="-1"></a> <span class="cf">with</span> torch.inference_mode():</span>
|
||
<span id="cb1-40"><a href="#cb1-40" aria-hidden="true" tabindex="-1"></a> codes <span class="op">=</span> model.encode(waveform)</span>
|
||
<span id="cb1-41"><a href="#cb1-41" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-42"><a href="#cb1-42" aria-hidden="true" tabindex="-1"></a> all_codes <span class="op">=</span> []</span>
|
||
<span id="cb1-43"><a href="#cb1-43" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> i <span class="kw">in</span> <span class="bu">range</span>(codes[<span class="dv">0</span>].shape[<span class="dv">1</span>]):</span>
|
||
<span id="cb1-44"><a href="#cb1-44" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">0</span>][<span class="dv">0</span>][i].item()<span class="op">+</span><span class="dv">128266</span>)</span>
|
||
<span id="cb1-45"><a href="#cb1-45" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">1</span>][<span class="dv">0</span>][<span class="dv">2</span><span class="op">*</span>i].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span><span class="dv">4096</span>)</span>
|
||
<span id="cb1-46"><a href="#cb1-46" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][<span class="dv">4</span><span class="op">*</span>i].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">2</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb1-47"><a href="#cb1-47" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][(<span class="dv">4</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">1</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">3</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb1-48"><a href="#cb1-48" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">1</span>][<span class="dv">0</span>][(<span class="dv">2</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">1</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">4</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb1-49"><a href="#cb1-49" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][(<span class="dv">4</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">2</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">5</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb1-50"><a href="#cb1-50" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][(<span class="dv">4</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">3</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">6</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb1-51"><a href="#cb1-51" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-52"><a href="#cb1-52" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-53"><a href="#cb1-53" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> all_codes</span>
|
||
<span id="cb1-54"><a href="#cb1-54" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-55"><a href="#cb1-55" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> add_codes(example):</span>
|
||
<span id="cb1-56"><a href="#cb1-56" aria-hidden="true" tabindex="-1"></a> <span class="co"># Always initialize codes_list to None</span></span>
|
||
<span id="cb1-57"><a href="#cb1-57" aria-hidden="true" tabindex="-1"></a> codes_list <span class="op">=</span> <span class="va">None</span></span>
|
||
<span id="cb1-58"><a href="#cb1-58" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-59"><a href="#cb1-59" aria-hidden="true" tabindex="-1"></a> <span class="cf">try</span>:</span>
|
||
<span id="cb1-60"><a href="#cb1-60" aria-hidden="true" tabindex="-1"></a> answer_audio <span class="op">=</span> example.get(<span class="st">"audio"</span>)</span>
|
||
<span id="cb1-61"><a href="#cb1-61" aria-hidden="true" tabindex="-1"></a> <span class="co"># If there's a valid audio array, tokenise it</span></span>
|
||
<span id="cb1-62"><a href="#cb1-62" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> answer_audio <span class="kw">and</span> <span class="st">"array"</span> <span class="kw">in</span> answer_audio:</span>
|
||
<span id="cb1-63"><a href="#cb1-63" aria-hidden="true" tabindex="-1"></a> audio_array <span class="op">=</span> answer_audio[<span class="st">"array"</span>]</span>
|
||
<span id="cb1-64"><a href="#cb1-64" aria-hidden="true" tabindex="-1"></a> codes_list <span class="op">=</span> tokenise_audio(audio_array)</span>
|
||
<span id="cb1-65"><a href="#cb1-65" aria-hidden="true" tabindex="-1"></a> <span class="cf">except</span> <span class="pp">Exception</span> <span class="im">as</span> e:</span>
|
||
<span id="cb1-66"><a href="#cb1-66" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"Skipping row due to error: </span><span class="sc">{</span>e<span class="sc">}</span><span class="ss">"</span>)</span>
|
||
<span id="cb1-67"><a href="#cb1-67" aria-hidden="true" tabindex="-1"></a> <span class="co"># Keep codes_list as None if we fail</span></span>
|
||
<span id="cb1-68"><a href="#cb1-68" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"codes_list"</span>] <span class="op">=</span> codes_list</span>
|
||
<span id="cb1-69"><a href="#cb1-69" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-70"><a href="#cb1-70" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> example</span>
|
||
<span id="cb1-71"><a href="#cb1-71" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-72"><a href="#cb1-72" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">map</span>(add_codes, remove_columns<span class="op">=</span>[<span class="st">"audio"</span>])</span>
|
||
<span id="cb1-73"><a href="#cb1-73" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-74"><a href="#cb1-74" aria-hidden="true" tabindex="-1"></a><span class="co">#@title Load Tokenizer</span></span>
|
||
<span id="cb1-75"><a href="#cb1-75" aria-hidden="true" tabindex="-1"></a>tokeniser_length <span class="op">=</span> <span class="dv">128256</span></span>
|
||
<span id="cb1-76"><a href="#cb1-76" aria-hidden="true" tabindex="-1"></a>start_of_text <span class="op">=</span> <span class="dv">128000</span></span>
|
||
<span id="cb1-77"><a href="#cb1-77" aria-hidden="true" tabindex="-1"></a>end_of_text <span class="op">=</span> <span class="dv">128009</span></span>
|
||
<span id="cb1-78"><a href="#cb1-78" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-79"><a href="#cb1-79" aria-hidden="true" tabindex="-1"></a>start_of_speech <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">1</span></span>
|
||
<span id="cb1-80"><a href="#cb1-80" aria-hidden="true" tabindex="-1"></a>end_of_speech <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">2</span></span>
|
||
<span id="cb1-81"><a href="#cb1-81" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-82"><a href="#cb1-82" aria-hidden="true" tabindex="-1"></a>start_of_human <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">3</span></span>
|
||
<span id="cb1-83"><a href="#cb1-83" aria-hidden="true" tabindex="-1"></a>end_of_human <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">4</span></span>
|
||
<span id="cb1-84"><a href="#cb1-84" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-85"><a href="#cb1-85" aria-hidden="true" tabindex="-1"></a>start_of_ai <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">5</span></span>
|
||
<span id="cb1-86"><a href="#cb1-86" aria-hidden="true" tabindex="-1"></a>end_of_ai <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">6</span></span>
|
||
<span id="cb1-87"><a href="#cb1-87" aria-hidden="true" tabindex="-1"></a>pad_token <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">7</span></span>
|
||
<span id="cb1-88"><a href="#cb1-88" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-89"><a href="#cb1-89" aria-hidden="true" tabindex="-1"></a>audio_tokens_start <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">10</span></span>
|
||
<span id="cb1-90"><a href="#cb1-90" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-91"><a href="#cb1-91" aria-hidden="true" tabindex="-1"></a>tokenizer_name <span class="op">=</span> <span class="st">"canopylabs/orpheus-3b-0.1-pretrained"</span></span>
|
||
<span id="cb1-92"><a href="#cb1-92" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-93"><a href="#cb1-93" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-94"><a href="#cb1-94" aria-hidden="true" tabindex="-1"></a>tokenizer <span class="op">=</span> AutoTokenizer.from_pretrained(tokenizer_name)</span>
|
||
<span id="cb1-95"><a href="#cb1-95" aria-hidden="true" tabindex="-1"></a>num_proc <span class="op">=</span> os.cpu_count() <span class="op">-</span> <span class="dv">2</span></span>
|
||
<span id="cb1-96"><a href="#cb1-96" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-97"><a href="#cb1-97" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">filter</span>(<span class="kw">lambda</span> x: x[<span class="st">"codes_list"</span>] <span class="kw">is</span> <span class="kw">not</span> <span class="va">None</span>)</span>
|
||
<span id="cb1-98"><a href="#cb1-98" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">filter</span>(<span class="kw">lambda</span> x: <span class="bu">len</span>(x[<span class="st">"codes_list"</span>]) <span class="op">></span> <span class="dv">0</span>)</span>
|
||
<span id="cb1-99"><a href="#cb1-99" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-100"><a href="#cb1-100" aria-hidden="true" tabindex="-1"></a><span class="co">#@title Create Input Ids</span></span>
|
||
<span id="cb1-101"><a href="#cb1-101" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> remove_duplicate_frames(example):</span>
|
||
<span id="cb1-102"><a href="#cb1-102" aria-hidden="true" tabindex="-1"></a> vals <span class="op">=</span> example[<span class="st">"codes_list"</span>]</span>
|
||
<span id="cb1-103"><a href="#cb1-103" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> <span class="bu">len</span>(vals) <span class="op">%</span> <span class="dv">7</span> <span class="op">!=</span> <span class="dv">0</span>:</span>
|
||
<span id="cb1-104"><a href="#cb1-104" aria-hidden="true" tabindex="-1"></a> <span class="cf">raise</span> <span class="pp">ValueError</span>(<span class="st">"Input list length must be divisible by 7"</span>)</span>
|
||
<span id="cb1-105"><a href="#cb1-105" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-106"><a href="#cb1-106" aria-hidden="true" tabindex="-1"></a> result <span class="op">=</span> vals[:<span class="dv">7</span>]</span>
|
||
<span id="cb1-107"><a href="#cb1-107" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-108"><a href="#cb1-108" aria-hidden="true" tabindex="-1"></a> removed_frames <span class="op">=</span> <span class="dv">0</span></span>
|
||
<span id="cb1-109"><a href="#cb1-109" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-110"><a href="#cb1-110" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> i <span class="kw">in</span> <span class="bu">range</span>(<span class="dv">7</span>, <span class="bu">len</span>(vals), <span class="dv">7</span>):</span>
|
||
<span id="cb1-111"><a href="#cb1-111" aria-hidden="true" tabindex="-1"></a> current_first <span class="op">=</span> vals[i]</span>
|
||
<span id="cb1-112"><a href="#cb1-112" aria-hidden="true" tabindex="-1"></a> previous_first <span class="op">=</span> result[<span class="op">-</span><span class="dv">7</span>]</span>
|
||
<span id="cb1-113"><a href="#cb1-113" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-114"><a href="#cb1-114" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> current_first <span class="op">!=</span> previous_first:</span>
|
||
<span id="cb1-115"><a href="#cb1-115" aria-hidden="true" tabindex="-1"></a> result.extend(vals[i:i<span class="op">+</span><span class="dv">7</span>])</span>
|
||
<span id="cb1-116"><a href="#cb1-116" aria-hidden="true" tabindex="-1"></a> <span class="cf">else</span>:</span>
|
||
<span id="cb1-117"><a href="#cb1-117" aria-hidden="true" tabindex="-1"></a> removed_frames <span class="op">+=</span> <span class="dv">1</span></span>
|
||
<span id="cb1-118"><a href="#cb1-118" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-119"><a href="#cb1-119" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"codes_list"</span>] <span class="op">=</span> result</span>
|
||
<span id="cb1-120"><a href="#cb1-120" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-121"><a href="#cb1-121" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> example</span>
|
||
<span id="cb1-122"><a href="#cb1-122" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-123"><a href="#cb1-123" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">map</span>(remove_duplicate_frames, num_proc<span class="op">=</span>num_proc)</span>
|
||
<span id="cb1-124"><a href="#cb1-124" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-125"><a href="#cb1-125" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-126"><a href="#cb1-126" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> create_input_ids(example):</span>
|
||
<span id="cb1-127"><a href="#cb1-127" aria-hidden="true" tabindex="-1"></a> text_ids <span class="op">=</span> tokenizer.encode({example[<span class="st">'text'</span>]}, add_special_tokens<span class="op">=</span><span class="va">True</span>)</span>
|
||
<span id="cb1-128"><a href="#cb1-128" aria-hidden="true" tabindex="-1"></a> text_ids.append(end_of_text)</span>
|
||
<span id="cb1-129"><a href="#cb1-129" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"text_tokens"</span>] <span class="op">=</span> text_ids</span>
|
||
<span id="cb1-130"><a href="#cb1-130" aria-hidden="true" tabindex="-1"></a> input_ids <span class="op">=</span> (</span>
|
||
<span id="cb1-131"><a href="#cb1-131" aria-hidden="true" tabindex="-1"></a> [start_of_human]</span>
|
||
<span id="cb1-132"><a href="#cb1-132" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> example[<span class="st">"text_tokens"</span>]</span>
|
||
<span id="cb1-133"><a href="#cb1-133" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [end_of_human]</span>
|
||
<span id="cb1-134"><a href="#cb1-134" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [start_of_ai]</span>
|
||
<span id="cb1-135"><a href="#cb1-135" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [start_of_speech]</span>
|
||
<span id="cb1-136"><a href="#cb1-136" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> example[<span class="st">"codes_list"</span>]</span>
|
||
<span id="cb1-137"><a href="#cb1-137" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [end_of_speech]</span>
|
||
<span id="cb1-138"><a href="#cb1-138" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [end_of_ai]</span>
|
||
<span id="cb1-139"><a href="#cb1-139" aria-hidden="true" tabindex="-1"></a> )</span>
|
||
<span id="cb1-140"><a href="#cb1-140" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"input_ids"</span>] <span class="op">=</span> input_ids</span>
|
||
<span id="cb1-141"><a href="#cb1-141" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"labels"</span>] <span class="op">=</span> input_ids</span>
|
||
<span id="cb1-142"><a href="#cb1-142" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"attention_mask"</span>] <span class="op">=</span> [<span class="dv">1</span>] <span class="op">*</span> <span class="bu">len</span>(input_ids)</span>
|
||
<span id="cb1-143"><a href="#cb1-143" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-144"><a href="#cb1-144" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> example</span>
|
||
<span id="cb1-145"><a href="#cb1-145" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-146"><a href="#cb1-146" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">map</span>(create_input_ids, num_proc<span class="op">=</span>num_proc, remove_columns<span class="op">=</span>[<span class="st">"text"</span>, <span class="st">"codes_list"</span>])</span>
|
||
<span id="cb1-147"><a href="#cb1-147" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-148"><a href="#cb1-148" aria-hidden="true" tabindex="-1"></a><span class="co">#@title Remove unnecessary columns</span></span>
|
||
<span id="cb1-149"><a href="#cb1-149" aria-hidden="true" tabindex="-1"></a>columns_to_keep <span class="op">=</span> [<span class="st">"input_ids"</span>, <span class="st">"labels"</span>, <span class="st">"attention_mask"</span>]</span>
|
||
<span id="cb1-150"><a href="#cb1-150" aria-hidden="true" tabindex="-1"></a>columns_to_remove <span class="op">=</span> [col <span class="cf">for</span> col <span class="kw">in</span> ds.column_names <span class="cf">if</span> col <span class="kw">not</span> <span class="kw">in</span> columns_to_keep]</span>
|
||
<span id="cb1-151"><a href="#cb1-151" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-152"><a href="#cb1-152" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.remove_columns(columns_to_remove)</span>
|
||
<span id="cb1-153"><a href="#cb1-153" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb1-154"><a href="#cb1-154" aria-hidden="true" tabindex="-1"></a>ds.push_to_hub(name_to_push_dataset_to)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||
</section>
|
||
<section id="finetune-pre-processing" class="level2">
|
||
<h2 class="anchored" data-anchor-id="finetune-pre-processing">Finetune pre-processing</h2>
|
||
<p>Use this code to add a new voice.</p>
|
||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> torch</span>
|
||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> snac <span class="im">import</span> SNAC</span>
|
||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> datasets <span class="im">import</span> load_dataset</span>
|
||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> huggingface_hub <span class="im">import</span> snapshot_download</span>
|
||
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> datasets <span class="im">import</span> load_dataset</span>
|
||
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> random</span>
|
||
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> torchaudio.transforms <span class="im">as</span> T</span>
|
||
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> transformers <span class="im">import</span> AutoTokenizer</span>
|
||
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> os</span>
|
||
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a>my_original_dataset_name <span class="op">=</span> <span class="st">"<huggingface-id-of-dataset-that-we-want-to-preprocess>"</span></span>
|
||
<span id="cb2-12"><a href="#cb2-12" aria-hidden="true" tabindex="-1"></a>name_to_push_dataset_to <span class="op">=</span> <span class="st">"<huggingface-id-of-where-to-save-dataset>"</span></span>
|
||
<span id="cb2-13"><a href="#cb2-13" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-14"><a href="#cb2-14" aria-hidden="true" tabindex="-1"></a>dsn <span class="op">=</span> my_original_dataset_name</span>
|
||
<span id="cb2-15"><a href="#cb2-15" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-16"><a href="#cb2-16" aria-hidden="true" tabindex="-1"></a>snapshot_download(</span>
|
||
<span id="cb2-17"><a href="#cb2-17" aria-hidden="true" tabindex="-1"></a> repo_id<span class="op">=</span>dsn,</span>
|
||
<span id="cb2-18"><a href="#cb2-18" aria-hidden="true" tabindex="-1"></a> repo_type<span class="op">=</span><span class="st">"dataset"</span>,</span>
|
||
<span id="cb2-19"><a href="#cb2-19" aria-hidden="true" tabindex="-1"></a> revision<span class="op">=</span><span class="st">"main"</span>,</span>
|
||
<span id="cb2-20"><a href="#cb2-20" aria-hidden="true" tabindex="-1"></a> max_workers<span class="op">=</span><span class="dv">64</span>,</span>
|
||
<span id="cb2-21"><a href="#cb2-21" aria-hidden="true" tabindex="-1"></a>)</span>
|
||
<span id="cb2-22"><a href="#cb2-22" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-23"><a href="#cb2-23" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-24"><a href="#cb2-24" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(dsn, split<span class="op">=</span><span class="st">"train"</span>)</span>
|
||
<span id="cb2-25"><a href="#cb2-25" aria-hidden="true" tabindex="-1"></a>ds_sample_rate <span class="op">=</span> ds[<span class="dv">0</span>][<span class="st">"audio"</span>][<span class="st">"sampling_rate"</span>]</span>
|
||
<span id="cb2-26"><a href="#cb2-26" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-27"><a href="#cb2-27" aria-hidden="true" tabindex="-1"></a>model <span class="op">=</span> SNAC.from_pretrained(<span class="st">"hubertsiuzdak/snac_24khz"</span>)</span>
|
||
<span id="cb2-28"><a href="#cb2-28" aria-hidden="true" tabindex="-1"></a>model <span class="op">=</span> model.to(<span class="st">"mps"</span>)</span>
|
||
<span id="cb2-29"><a href="#cb2-29" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-30"><a href="#cb2-30" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> tokenise_audio(waveform):</span>
|
||
<span id="cb2-31"><a href="#cb2-31" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> torch.from_numpy(waveform).unsqueeze(<span class="dv">0</span>)</span>
|
||
<span id="cb2-32"><a href="#cb2-32" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> waveform.to(dtype<span class="op">=</span>torch.float32)</span>
|
||
<span id="cb2-33"><a href="#cb2-33" aria-hidden="true" tabindex="-1"></a> resample_transform <span class="op">=</span> T.Resample(orig_freq<span class="op">=</span>ds_sample_rate, new_freq<span class="op">=</span><span class="dv">24000</span>)</span>
|
||
<span id="cb2-34"><a href="#cb2-34" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> resample_transform(waveform)</span>
|
||
<span id="cb2-35"><a href="#cb2-35" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-36"><a href="#cb2-36" aria-hidden="true" tabindex="-1"></a> waveform <span class="op">=</span> waveform.unsqueeze(<span class="dv">0</span>).to(<span class="st">"cuda"</span>)</span>
|
||
<span id="cb2-37"><a href="#cb2-37" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-38"><a href="#cb2-38" aria-hidden="true" tabindex="-1"></a> <span class="co">#generate the codes from snac</span></span>
|
||
<span id="cb2-39"><a href="#cb2-39" aria-hidden="true" tabindex="-1"></a> <span class="cf">with</span> torch.inference_mode():</span>
|
||
<span id="cb2-40"><a href="#cb2-40" aria-hidden="true" tabindex="-1"></a> codes <span class="op">=</span> model.encode(waveform)</span>
|
||
<span id="cb2-41"><a href="#cb2-41" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-42"><a href="#cb2-42" aria-hidden="true" tabindex="-1"></a> all_codes <span class="op">=</span> []</span>
|
||
<span id="cb2-43"><a href="#cb2-43" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> i <span class="kw">in</span> <span class="bu">range</span>(codes[<span class="dv">0</span>].shape[<span class="dv">1</span>]):</span>
|
||
<span id="cb2-44"><a href="#cb2-44" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">0</span>][<span class="dv">0</span>][i].item()<span class="op">+</span><span class="dv">128266</span>)</span>
|
||
<span id="cb2-45"><a href="#cb2-45" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">1</span>][<span class="dv">0</span>][<span class="dv">2</span><span class="op">*</span>i].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span><span class="dv">4096</span>)</span>
|
||
<span id="cb2-46"><a href="#cb2-46" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][<span class="dv">4</span><span class="op">*</span>i].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">2</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb2-47"><a href="#cb2-47" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][(<span class="dv">4</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">1</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">3</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb2-48"><a href="#cb2-48" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">1</span>][<span class="dv">0</span>][(<span class="dv">2</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">1</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">4</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb2-49"><a href="#cb2-49" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][(<span class="dv">4</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">2</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">5</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb2-50"><a href="#cb2-50" aria-hidden="true" tabindex="-1"></a> all_codes.append(codes[<span class="dv">2</span>][<span class="dv">0</span>][(<span class="dv">4</span><span class="op">*</span>i)<span class="op">+</span><span class="dv">3</span>].item()<span class="op">+</span><span class="dv">128266</span><span class="op">+</span>(<span class="dv">6</span><span class="op">*</span><span class="dv">4096</span>))</span>
|
||
<span id="cb2-51"><a href="#cb2-51" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-52"><a href="#cb2-52" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-53"><a href="#cb2-53" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> all_codes</span>
|
||
<span id="cb2-54"><a href="#cb2-54" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-55"><a href="#cb2-55" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> add_codes(example):</span>
|
||
<span id="cb2-56"><a href="#cb2-56" aria-hidden="true" tabindex="-1"></a> <span class="co"># Always initialize codes_list to None</span></span>
|
||
<span id="cb2-57"><a href="#cb2-57" aria-hidden="true" tabindex="-1"></a> codes_list <span class="op">=</span> <span class="va">None</span></span>
|
||
<span id="cb2-58"><a href="#cb2-58" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-59"><a href="#cb2-59" aria-hidden="true" tabindex="-1"></a> <span class="cf">try</span>:</span>
|
||
<span id="cb2-60"><a href="#cb2-60" aria-hidden="true" tabindex="-1"></a> answer_audio <span class="op">=</span> example.get(<span class="st">"audio"</span>)</span>
|
||
<span id="cb2-61"><a href="#cb2-61" aria-hidden="true" tabindex="-1"></a> <span class="co"># If there's a valid audio array, tokenise it</span></span>
|
||
<span id="cb2-62"><a href="#cb2-62" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> answer_audio <span class="kw">and</span> <span class="st">"array"</span> <span class="kw">in</span> answer_audio:</span>
|
||
<span id="cb2-63"><a href="#cb2-63" aria-hidden="true" tabindex="-1"></a> audio_array <span class="op">=</span> answer_audio[<span class="st">"array"</span>]</span>
|
||
<span id="cb2-64"><a href="#cb2-64" aria-hidden="true" tabindex="-1"></a> codes_list <span class="op">=</span> tokenise_audio(audio_array)</span>
|
||
<span id="cb2-65"><a href="#cb2-65" aria-hidden="true" tabindex="-1"></a> <span class="cf">except</span> <span class="pp">Exception</span> <span class="im">as</span> e:</span>
|
||
<span id="cb2-66"><a href="#cb2-66" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"Skipping row due to error: </span><span class="sc">{</span>e<span class="sc">}</span><span class="ss">"</span>)</span>
|
||
<span id="cb2-67"><a href="#cb2-67" aria-hidden="true" tabindex="-1"></a> <span class="co"># Keep codes_list as None if we fail</span></span>
|
||
<span id="cb2-68"><a href="#cb2-68" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"codes_list"</span>] <span class="op">=</span> codes_list</span>
|
||
<span id="cb2-69"><a href="#cb2-69" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-70"><a href="#cb2-70" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> example</span>
|
||
<span id="cb2-71"><a href="#cb2-71" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-72"><a href="#cb2-72" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">map</span>(add_codes, remove_columns<span class="op">=</span>[<span class="st">"audio"</span>])</span>
|
||
<span id="cb2-73"><a href="#cb2-73" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-74"><a href="#cb2-74" aria-hidden="true" tabindex="-1"></a><span class="co">#@title Load Tokenizer</span></span>
|
||
<span id="cb2-75"><a href="#cb2-75" aria-hidden="true" tabindex="-1"></a>tokeniser_length <span class="op">=</span> <span class="dv">128256</span></span>
|
||
<span id="cb2-76"><a href="#cb2-76" aria-hidden="true" tabindex="-1"></a>start_of_text <span class="op">=</span> <span class="dv">128000</span></span>
|
||
<span id="cb2-77"><a href="#cb2-77" aria-hidden="true" tabindex="-1"></a>end_of_text <span class="op">=</span> <span class="dv">128009</span></span>
|
||
<span id="cb2-78"><a href="#cb2-78" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-79"><a href="#cb2-79" aria-hidden="true" tabindex="-1"></a>start_of_speech <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">1</span></span>
|
||
<span id="cb2-80"><a href="#cb2-80" aria-hidden="true" tabindex="-1"></a>end_of_speech <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">2</span></span>
|
||
<span id="cb2-81"><a href="#cb2-81" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-82"><a href="#cb2-82" aria-hidden="true" tabindex="-1"></a>start_of_human <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">3</span></span>
|
||
<span id="cb2-83"><a href="#cb2-83" aria-hidden="true" tabindex="-1"></a>end_of_human <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">4</span></span>
|
||
<span id="cb2-84"><a href="#cb2-84" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-85"><a href="#cb2-85" aria-hidden="true" tabindex="-1"></a>start_of_ai <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">5</span></span>
|
||
<span id="cb2-86"><a href="#cb2-86" aria-hidden="true" tabindex="-1"></a>end_of_ai <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">6</span></span>
|
||
<span id="cb2-87"><a href="#cb2-87" aria-hidden="true" tabindex="-1"></a>pad_token <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">7</span></span>
|
||
<span id="cb2-88"><a href="#cb2-88" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-89"><a href="#cb2-89" aria-hidden="true" tabindex="-1"></a>audio_tokens_start <span class="op">=</span> tokeniser_length <span class="op">+</span> <span class="dv">10</span></span>
|
||
<span id="cb2-90"><a href="#cb2-90" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-91"><a href="#cb2-91" aria-hidden="true" tabindex="-1"></a>tokenizer_name <span class="op">=</span> <span class="st">"canopylabs/orpheus-3b-0.1-pretrained"</span></span>
|
||
<span id="cb2-92"><a href="#cb2-92" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-93"><a href="#cb2-93" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-94"><a href="#cb2-94" aria-hidden="true" tabindex="-1"></a>tokenizer <span class="op">=</span> AutoTokenizer.from_pretrained(tokenizer_name)</span>
|
||
<span id="cb2-95"><a href="#cb2-95" aria-hidden="true" tabindex="-1"></a>num_proc <span class="op">=</span> os.cpu_count() <span class="op">-</span> <span class="dv">2</span></span>
|
||
<span id="cb2-96"><a href="#cb2-96" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-97"><a href="#cb2-97" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">filter</span>(<span class="kw">lambda</span> x: x[<span class="st">"codes_list"</span>] <span class="kw">is</span> <span class="kw">not</span> <span class="va">None</span>)</span>
|
||
<span id="cb2-98"><a href="#cb2-98" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">filter</span>(<span class="kw">lambda</span> x: <span class="bu">len</span>(x[<span class="st">"codes_list"</span>]) <span class="op">></span> <span class="dv">0</span>)</span>
|
||
<span id="cb2-99"><a href="#cb2-99" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-100"><a href="#cb2-100" aria-hidden="true" tabindex="-1"></a><span class="co">#@title Create Input Ids</span></span>
|
||
<span id="cb2-101"><a href="#cb2-101" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> remove_duplicate_frames(example):</span>
|
||
<span id="cb2-102"><a href="#cb2-102" aria-hidden="true" tabindex="-1"></a> vals <span class="op">=</span> example[<span class="st">"codes_list"</span>]</span>
|
||
<span id="cb2-103"><a href="#cb2-103" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> <span class="bu">len</span>(vals) <span class="op">%</span> <span class="dv">7</span> <span class="op">!=</span> <span class="dv">0</span>:</span>
|
||
<span id="cb2-104"><a href="#cb2-104" aria-hidden="true" tabindex="-1"></a> <span class="cf">raise</span> <span class="pp">ValueError</span>(<span class="st">"Input list length must be divisible by 7"</span>)</span>
|
||
<span id="cb2-105"><a href="#cb2-105" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-106"><a href="#cb2-106" aria-hidden="true" tabindex="-1"></a> result <span class="op">=</span> vals[:<span class="dv">7</span>]</span>
|
||
<span id="cb2-107"><a href="#cb2-107" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-108"><a href="#cb2-108" aria-hidden="true" tabindex="-1"></a> removed_frames <span class="op">=</span> <span class="dv">0</span></span>
|
||
<span id="cb2-109"><a href="#cb2-109" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-110"><a href="#cb2-110" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> i <span class="kw">in</span> <span class="bu">range</span>(<span class="dv">7</span>, <span class="bu">len</span>(vals), <span class="dv">7</span>):</span>
|
||
<span id="cb2-111"><a href="#cb2-111" aria-hidden="true" tabindex="-1"></a> current_first <span class="op">=</span> vals[i]</span>
|
||
<span id="cb2-112"><a href="#cb2-112" aria-hidden="true" tabindex="-1"></a> previous_first <span class="op">=</span> result[<span class="op">-</span><span class="dv">7</span>]</span>
|
||
<span id="cb2-113"><a href="#cb2-113" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-114"><a href="#cb2-114" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> current_first <span class="op">!=</span> previous_first:</span>
|
||
<span id="cb2-115"><a href="#cb2-115" aria-hidden="true" tabindex="-1"></a> result.extend(vals[i:i<span class="op">+</span><span class="dv">7</span>])</span>
|
||
<span id="cb2-116"><a href="#cb2-116" aria-hidden="true" tabindex="-1"></a> <span class="cf">else</span>:</span>
|
||
<span id="cb2-117"><a href="#cb2-117" aria-hidden="true" tabindex="-1"></a> removed_frames <span class="op">+=</span> <span class="dv">1</span></span>
|
||
<span id="cb2-118"><a href="#cb2-118" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-119"><a href="#cb2-119" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"codes_list"</span>] <span class="op">=</span> result</span>
|
||
<span id="cb2-120"><a href="#cb2-120" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-121"><a href="#cb2-121" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> example</span>
|
||
<span id="cb2-122"><a href="#cb2-122" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-123"><a href="#cb2-123" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">map</span>(remove_duplicate_frames, num_proc<span class="op">=</span>num_proc)</span>
|
||
<span id="cb2-124"><a href="#cb2-124" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-125"><a href="#cb2-125" aria-hidden="true" tabindex="-1"></a>tok_info <span class="op">=</span> <span class="st">'''*** HERE you can modify the text prompt</span></span>
|
||
<span id="cb2-126"><a href="#cb2-126" aria-hidden="true" tabindex="-1"></a><span class="st">i.e. if you wanted a multispeaker model like canopylabs/orpheus-3b-0.1-ft, you can pass:</span></span>
|
||
<span id="cb2-127"><a href="#cb2-127" aria-hidden="true" tabindex="-1"></a><span class="st">f"</span><span class="sc">{example["source"]}</span><span class="st">: </span><span class="sc">{example["text"]}</span><span class="st">", as is passed.</span></span>
|
||
<span id="cb2-128"><a href="#cb2-128" aria-hidden="true" tabindex="-1"></a><span class="st">'''</span></span>
|
||
<span id="cb2-129"><a href="#cb2-129" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(tok_info)</span>
|
||
<span id="cb2-130"><a href="#cb2-130" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-131"><a href="#cb2-131" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> create_input_ids(example):</span>
|
||
<span id="cb2-132"><a href="#cb2-132" aria-hidden="true" tabindex="-1"></a> text_ids <span class="op">=</span> tokenizer.encode(<span class="ss">f"</span><span class="sc">{</span>example[<span class="st">'speaker_id'</span>]<span class="sc">}</span><span class="ss">: </span><span class="sc">{</span>example[<span class="st">'text'</span>]<span class="sc">}</span><span class="ss">"</span>, add_special_tokens<span class="op">=</span><span class="va">True</span>)</span>
|
||
<span id="cb2-133"><a href="#cb2-133" aria-hidden="true" tabindex="-1"></a> text_ids.append(end_of_text)</span>
|
||
<span id="cb2-134"><a href="#cb2-134" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"text_tokens"</span>] <span class="op">=</span> text_ids</span>
|
||
<span id="cb2-135"><a href="#cb2-135" aria-hidden="true" tabindex="-1"></a> input_ids <span class="op">=</span> (</span>
|
||
<span id="cb2-136"><a href="#cb2-136" aria-hidden="true" tabindex="-1"></a> [start_of_human]</span>
|
||
<span id="cb2-137"><a href="#cb2-137" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> example[<span class="st">"text_tokens"</span>]</span>
|
||
<span id="cb2-138"><a href="#cb2-138" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [end_of_human]</span>
|
||
<span id="cb2-139"><a href="#cb2-139" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [start_of_ai]</span>
|
||
<span id="cb2-140"><a href="#cb2-140" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [start_of_speech]</span>
|
||
<span id="cb2-141"><a href="#cb2-141" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> example[<span class="st">"codes_list"</span>]</span>
|
||
<span id="cb2-142"><a href="#cb2-142" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [end_of_speech]</span>
|
||
<span id="cb2-143"><a href="#cb2-143" aria-hidden="true" tabindex="-1"></a> <span class="op">+</span> [end_of_ai]</span>
|
||
<span id="cb2-144"><a href="#cb2-144" aria-hidden="true" tabindex="-1"></a> )</span>
|
||
<span id="cb2-145"><a href="#cb2-145" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"input_ids"</span>] <span class="op">=</span> input_ids</span>
|
||
<span id="cb2-146"><a href="#cb2-146" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"labels"</span>] <span class="op">=</span> input_ids</span>
|
||
<span id="cb2-147"><a href="#cb2-147" aria-hidden="true" tabindex="-1"></a> example[<span class="st">"attention_mask"</span>] <span class="op">=</span> [<span class="dv">1</span>] <span class="op">*</span> <span class="bu">len</span>(input_ids)</span>
|
||
<span id="cb2-148"><a href="#cb2-148" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-149"><a href="#cb2-149" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> example</span>
|
||
<span id="cb2-150"><a href="#cb2-150" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-151"><a href="#cb2-151" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.<span class="bu">map</span>(create_input_ids, num_proc<span class="op">=</span>num_proc, remove_columns<span class="op">=</span>[<span class="st">"text"</span>, <span class="st">"codes_list"</span>])</span>
|
||
<span id="cb2-152"><a href="#cb2-152" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-153"><a href="#cb2-153" aria-hidden="true" tabindex="-1"></a><span class="co">#@title Remove unnecessary columns</span></span>
|
||
<span id="cb2-154"><a href="#cb2-154" aria-hidden="true" tabindex="-1"></a>columns_to_keep <span class="op">=</span> [<span class="st">"input_ids"</span>, <span class="st">"labels"</span>, <span class="st">"attention_mask"</span>]</span>
|
||
<span id="cb2-155"><a href="#cb2-155" aria-hidden="true" tabindex="-1"></a>columns_to_remove <span class="op">=</span> [col <span class="cf">for</span> col <span class="kw">in</span> ds.column_names <span class="cf">if</span> col <span class="kw">not</span> <span class="kw">in</span> columns_to_keep]</span>
|
||
<span id="cb2-156"><a href="#cb2-156" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-157"><a href="#cb2-157" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> ds.remove_columns(columns_to_remove)</span>
|
||
<span id="cb2-158"><a href="#cb2-158" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-159"><a href="#cb2-159" aria-hidden="true" tabindex="-1"></a>ds.push_to_hub(name_to_push_dataset_to)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||
</section>
|
||
<section id="training" class="level2">
|
||
<h2 class="anchored" data-anchor-id="training">Training</h2>
|
||
<p>After preprocessing is done, fill out the blanks in finetune.yml and simply run <code>axolotl train finetune.yml</code></p>
|
||
</section>
|
||
<section id="inference" class="level2">
|
||
<h2 class="anchored" data-anchor-id="inference">Inference</h2>
|
||
<p>For inference, please refer to the original <a href="https://github.com/canopyai/Orpheus-TTS/tree/main">orpheus github</a>.</p>
|
||
|
||
|
||
</section>
|
||
|
||
</main> <!-- /main -->
|
||
<script id="quarto-html-after-body" type="application/javascript">
|
||
window.document.addEventListener("DOMContentLoaded", function (event) {
|
||
const icon = "";
|
||
const anchorJS = new window.AnchorJS();
|
||
anchorJS.options = {
|
||
placement: 'right',
|
||
icon: icon
|
||
};
|
||
anchorJS.add('.anchored');
|
||
const isCodeAnnotation = (el) => {
|
||
for (const clz of el.classList) {
|
||
if (clz.startsWith('code-annotation-')) {
|
||
return true;
|
||
}
|
||
}
|
||
return false;
|
||
}
|
||
const onCopySuccess = function(e) {
|
||
// button target
|
||
const button = e.trigger;
|
||
// don't keep focus
|
||
button.blur();
|
||
// flash "checked"
|
||
button.classList.add('code-copy-button-checked');
|
||
var currentTitle = button.getAttribute("title");
|
||
button.setAttribute("title", "Copied!");
|
||
let tooltip;
|
||
if (window.bootstrap) {
|
||
button.setAttribute("data-bs-toggle", "tooltip");
|
||
button.setAttribute("data-bs-placement", "left");
|
||
button.setAttribute("data-bs-title", "Copied!");
|
||
tooltip = new bootstrap.Tooltip(button,
|
||
{ trigger: "manual",
|
||
customClass: "code-copy-button-tooltip",
|
||
offset: [0, -8]});
|
||
tooltip.show();
|
||
}
|
||
setTimeout(function() {
|
||
if (tooltip) {
|
||
tooltip.hide();
|
||
button.removeAttribute("data-bs-title");
|
||
button.removeAttribute("data-bs-toggle");
|
||
button.removeAttribute("data-bs-placement");
|
||
}
|
||
button.setAttribute("title", currentTitle);
|
||
button.classList.remove('code-copy-button-checked');
|
||
}, 1000);
|
||
// clear code selection
|
||
e.clearSelection();
|
||
}
|
||
const getTextToCopy = function(trigger) {
|
||
const outerScaffold = trigger.parentElement.cloneNode(true);
|
||
const codeEl = outerScaffold.querySelector('code');
|
||
for (const childEl of codeEl.children) {
|
||
if (isCodeAnnotation(childEl)) {
|
||
childEl.remove();
|
||
}
|
||
}
|
||
return codeEl.innerText;
|
||
}
|
||
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
|
||
text: getTextToCopy
|
||
});
|
||
clipboard.on('success', onCopySuccess);
|
||
if (window.document.getElementById('quarto-embedded-source-code-modal')) {
|
||
const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', {
|
||
text: getTextToCopy,
|
||
container: window.document.getElementById('quarto-embedded-source-code-modal')
|
||
});
|
||
clipboardModal.on('success', onCopySuccess);
|
||
}
|
||
var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
|
||
var mailtoRegex = new RegExp(/^mailto:/);
|
||
var filterRegex = new RegExp("https:\/\/docs\.axolotl\.ai");
|
||
var isInternal = (href) => {
|
||
return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href);
|
||
}
|
||
// Inspect non-navigation links and adorn them if external
|
||
var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool):not(.about-link)');
|
||
for (var i=0; i<links.length; i++) {
|
||
const link = links[i];
|
||
if (!isInternal(link.href)) {
|
||
// undo the damage that might have been done by quarto-nav.js in the case of
|
||
// links that we want to consider external
|
||
if (link.dataset.originalHref !== undefined) {
|
||
link.href = link.dataset.originalHref;
|
||
}
|
||
}
|
||
}
|
||
function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) {
|
||
const config = {
|
||
allowHTML: true,
|
||
maxWidth: 500,
|
||
delay: 100,
|
||
arrow: false,
|
||
appendTo: function(el) {
|
||
return el.parentElement;
|
||
},
|
||
interactive: true,
|
||
interactiveBorder: 10,
|
||
theme: 'quarto',
|
||
placement: 'bottom-start',
|
||
};
|
||
if (contentFn) {
|
||
config.content = contentFn;
|
||
}
|
||
if (onTriggerFn) {
|
||
config.onTrigger = onTriggerFn;
|
||
}
|
||
if (onUntriggerFn) {
|
||
config.onUntrigger = onUntriggerFn;
|
||
}
|
||
window.tippy(el, config);
|
||
}
|
||
const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
|
||
for (var i=0; i<noterefs.length; i++) {
|
||
const ref = noterefs[i];
|
||
tippyHover(ref, function() {
|
||
// use id or data attribute instead here
|
||
let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
|
||
try { href = new URL(href).hash; } catch {}
|
||
const id = href.replace(/^#\/?/, "");
|
||
const note = window.document.getElementById(id);
|
||
if (note) {
|
||
return note.innerHTML;
|
||
} else {
|
||
return "";
|
||
}
|
||
});
|
||
}
|
||
const xrefs = window.document.querySelectorAll('a.quarto-xref');
|
||
const processXRef = (id, note) => {
|
||
// Strip column container classes
|
||
const stripColumnClz = (el) => {
|
||
el.classList.remove("page-full", "page-columns");
|
||
if (el.children) {
|
||
for (const child of el.children) {
|
||
stripColumnClz(child);
|
||
}
|
||
}
|
||
}
|
||
stripColumnClz(note)
|
||
if (id === null || id.startsWith('sec-')) {
|
||
// Special case sections, only their first couple elements
|
||
const container = document.createElement("div");
|
||
if (note.children && note.children.length > 2) {
|
||
container.appendChild(note.children[0].cloneNode(true));
|
||
for (let i = 1; i < note.children.length; i++) {
|
||
const child = note.children[i];
|
||
if (child.tagName === "P" && child.innerText === "") {
|
||
continue;
|
||
} else {
|
||
container.appendChild(child.cloneNode(true));
|
||
break;
|
||
}
|
||
}
|
||
if (window.Quarto?.typesetMath) {
|
||
window.Quarto.typesetMath(container);
|
||
}
|
||
return container.innerHTML
|
||
} else {
|
||
if (window.Quarto?.typesetMath) {
|
||
window.Quarto.typesetMath(note);
|
||
}
|
||
return note.innerHTML;
|
||
}
|
||
} else {
|
||
// Remove any anchor links if they are present
|
||
const anchorLink = note.querySelector('a.anchorjs-link');
|
||
if (anchorLink) {
|
||
anchorLink.remove();
|
||
}
|
||
if (window.Quarto?.typesetMath) {
|
||
window.Quarto.typesetMath(note);
|
||
}
|
||
if (note.classList.contains("callout")) {
|
||
return note.outerHTML;
|
||
} else {
|
||
return note.innerHTML;
|
||
}
|
||
}
|
||
}
|
||
for (var i=0; i<xrefs.length; i++) {
|
||
const xref = xrefs[i];
|
||
tippyHover(xref, undefined, function(instance) {
|
||
instance.disable();
|
||
let url = xref.getAttribute('href');
|
||
let hash = undefined;
|
||
if (url.startsWith('#')) {
|
||
hash = url;
|
||
} else {
|
||
try { hash = new URL(url).hash; } catch {}
|
||
}
|
||
if (hash) {
|
||
const id = hash.replace(/^#\/?/, "");
|
||
const note = window.document.getElementById(id);
|
||
if (note !== null) {
|
||
try {
|
||
const html = processXRef(id, note.cloneNode(true));
|
||
instance.setContent(html);
|
||
} finally {
|
||
instance.enable();
|
||
instance.show();
|
||
}
|
||
} else {
|
||
// See if we can fetch this
|
||
fetch(url.split('#')[0])
|
||
.then(res => res.text())
|
||
.then(html => {
|
||
const parser = new DOMParser();
|
||
const htmlDoc = parser.parseFromString(html, "text/html");
|
||
const note = htmlDoc.getElementById(id);
|
||
if (note !== null) {
|
||
const html = processXRef(id, note);
|
||
instance.setContent(html);
|
||
}
|
||
}).finally(() => {
|
||
instance.enable();
|
||
instance.show();
|
||
});
|
||
}
|
||
} else {
|
||
// See if we can fetch a full url (with no hash to target)
|
||
// This is a special case and we should probably do some content thinning / targeting
|
||
fetch(url)
|
||
.then(res => res.text())
|
||
.then(html => {
|
||
const parser = new DOMParser();
|
||
const htmlDoc = parser.parseFromString(html, "text/html");
|
||
const note = htmlDoc.querySelector('main.content');
|
||
if (note !== null) {
|
||
// This should only happen for chapter cross references
|
||
// (since there is no id in the URL)
|
||
// remove the first header
|
||
if (note.children.length > 0 && note.children[0].tagName === "HEADER") {
|
||
note.children[0].remove();
|
||
}
|
||
const html = processXRef(null, note);
|
||
instance.setContent(html);
|
||
}
|
||
}).finally(() => {
|
||
instance.enable();
|
||
instance.show();
|
||
});
|
||
}
|
||
}, function(instance) {
|
||
});
|
||
}
|
||
let selectedAnnoteEl;
|
||
const selectorForAnnotation = ( cell, annotation) => {
|
||
let cellAttr = 'data-code-cell="' + cell + '"';
|
||
let lineAttr = 'data-code-annotation="' + annotation + '"';
|
||
const selector = 'span[' + cellAttr + '][' + lineAttr + ']';
|
||
return selector;
|
||
}
|
||
const selectCodeLines = (annoteEl) => {
|
||
const doc = window.document;
|
||
const targetCell = annoteEl.getAttribute("data-target-cell");
|
||
const targetAnnotation = annoteEl.getAttribute("data-target-annotation");
|
||
const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation));
|
||
const lines = annoteSpan.getAttribute("data-code-lines").split(",");
|
||
const lineIds = lines.map((line) => {
|
||
return targetCell + "-" + line;
|
||
})
|
||
let top = null;
|
||
let height = null;
|
||
let parent = null;
|
||
if (lineIds.length > 0) {
|
||
//compute the position of the single el (top and bottom and make a div)
|
||
const el = window.document.getElementById(lineIds[0]);
|
||
top = el.offsetTop;
|
||
height = el.offsetHeight;
|
||
parent = el.parentElement.parentElement;
|
||
if (lineIds.length > 1) {
|
||
const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]);
|
||
const bottom = lastEl.offsetTop + lastEl.offsetHeight;
|
||
height = bottom - top;
|
||
}
|
||
if (top !== null && height !== null && parent !== null) {
|
||
// cook up a div (if necessary) and position it
|
||
let div = window.document.getElementById("code-annotation-line-highlight");
|
||
if (div === null) {
|
||
div = window.document.createElement("div");
|
||
div.setAttribute("id", "code-annotation-line-highlight");
|
||
div.style.position = 'absolute';
|
||
parent.appendChild(div);
|
||
}
|
||
div.style.top = top - 2 + "px";
|
||
div.style.height = height + 4 + "px";
|
||
div.style.left = 0;
|
||
let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter");
|
||
if (gutterDiv === null) {
|
||
gutterDiv = window.document.createElement("div");
|
||
gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter");
|
||
gutterDiv.style.position = 'absolute';
|
||
const codeCell = window.document.getElementById(targetCell);
|
||
const gutter = codeCell.querySelector('.code-annotation-gutter');
|
||
gutter.appendChild(gutterDiv);
|
||
}
|
||
gutterDiv.style.top = top - 2 + "px";
|
||
gutterDiv.style.height = height + 4 + "px";
|
||
}
|
||
selectedAnnoteEl = annoteEl;
|
||
}
|
||
};
|
||
const unselectCodeLines = () => {
|
||
const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"];
|
||
elementsIds.forEach((elId) => {
|
||
const div = window.document.getElementById(elId);
|
||
if (div) {
|
||
div.remove();
|
||
}
|
||
});
|
||
selectedAnnoteEl = undefined;
|
||
};
|
||
// Handle positioning of the toggle
|
||
window.addEventListener(
|
||
"resize",
|
||
throttle(() => {
|
||
elRect = undefined;
|
||
if (selectedAnnoteEl) {
|
||
selectCodeLines(selectedAnnoteEl);
|
||
}
|
||
}, 10)
|
||
);
|
||
function throttle(fn, ms) {
|
||
let throttle = false;
|
||
let timer;
|
||
return (...args) => {
|
||
if(!throttle) { // first call gets through
|
||
fn.apply(this, args);
|
||
throttle = true;
|
||
} else { // all the others get throttled
|
||
if(timer) clearTimeout(timer); // cancel #2
|
||
timer = setTimeout(() => {
|
||
fn.apply(this, args);
|
||
timer = throttle = false;
|
||
}, ms);
|
||
}
|
||
};
|
||
}
|
||
// Attach click handler to the DT
|
||
const annoteDls = window.document.querySelectorAll('dt[data-target-cell]');
|
||
for (const annoteDlNode of annoteDls) {
|
||
annoteDlNode.addEventListener('click', (event) => {
|
||
const clickedEl = event.target;
|
||
if (clickedEl !== selectedAnnoteEl) {
|
||
unselectCodeLines();
|
||
const activeEl = window.document.querySelector('dt[data-target-cell].code-annotation-active');
|
||
if (activeEl) {
|
||
activeEl.classList.remove('code-annotation-active');
|
||
}
|
||
selectCodeLines(clickedEl);
|
||
clickedEl.classList.add('code-annotation-active');
|
||
} else {
|
||
// Unselect the line
|
||
unselectCodeLines();
|
||
clickedEl.classList.remove('code-annotation-active');
|
||
}
|
||
});
|
||
}
|
||
const findCites = (el) => {
|
||
const parentEl = el.parentElement;
|
||
if (parentEl) {
|
||
const cites = parentEl.dataset.cites;
|
||
if (cites) {
|
||
return {
|
||
el,
|
||
cites: cites.split(' ')
|
||
};
|
||
} else {
|
||
return findCites(el.parentElement)
|
||
}
|
||
} else {
|
||
return undefined;
|
||
}
|
||
};
|
||
var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
|
||
for (var i=0; i<bibliorefs.length; i++) {
|
||
const ref = bibliorefs[i];
|
||
const citeInfo = findCites(ref);
|
||
if (citeInfo) {
|
||
tippyHover(citeInfo.el, function() {
|
||
var popup = window.document.createElement('div');
|
||
citeInfo.cites.forEach(function(cite) {
|
||
var citeDiv = window.document.createElement('div');
|
||
citeDiv.classList.add('hanging-indent');
|
||
citeDiv.classList.add('csl-entry');
|
||
var biblioDiv = window.document.getElementById('ref-' + cite);
|
||
if (biblioDiv) {
|
||
citeDiv.innerHTML = biblioDiv.innerHTML;
|
||
}
|
||
popup.appendChild(citeDiv);
|
||
});
|
||
return popup.innerHTML;
|
||
});
|
||
}
|
||
}
|
||
});
|
||
</script>
|
||
</div> <!-- /content -->
|
||
|
||
|
||
|
||
|
||
</body></html> |