Server
/
fish-speech


			
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937
							
<!doctype html>
<html lang="pt" class="no-js">
  <head>
    
      <meta charset="utf-8">
      <meta name="viewport" content="width=device-width,initial-scale=1">
      
        <meta name="description" content="Targeting SOTA TTS solutions.">
      
      
        <link rel="canonical" href="https://speech.fish.audio/pt/finetune/">
      
      
        <link rel="prev" href="../install/">
      
      
        <link rel="next" href="../inference/">
      
      
          <link rel="alternate" href="../../finetune/" hreflang="en">
        
          <link rel="alternate" href="../../zh/finetune/" hreflang="zh">
        
          <link rel="alternate" href="../../ja/finetune/" hreflang="ja">
        
          <link rel="alternate" href="./" hreflang="pt">
        
          <link rel="alternate" href="../../ko/finetune/" hreflang="ko">
        
          <link rel="alternate" href="../../ar/finetune/" hreflang="ar">
        
      
      <link rel="icon" href="../../assets/logo.svg">
      <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.1">
    
    
        <title>Ajuste Fino - Fish Audio</title>
      
    
      <link rel="stylesheet" href="../../assets/stylesheets/main.484c7ddc.min.css">
      
        
        <link rel="stylesheet" href="../../assets/stylesheets/palette.ab4e12ef.min.css">
      
      
        <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
        <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
        <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
      
    
      <link rel="stylesheet" href="../../stylesheets/extra.css">
    
    <script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
    
      
  </head>
  
  
    <body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
  
    
    <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
    <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
    <label class="md-overlay" for="__drawer"></label>
    <div data-md-component="skip">
      
        
        <a href="#ajuste-fino-fine-tuning" class="md-skip">
          Ir para o conteúdo
        </a>
      
    </div>
    <div data-md-component="announce">
      
    </div>
    
    
<header class="md-header md-header--shadow" data-md-component="header">
  <nav class="md-header__inner md-grid" aria-label="Cabeçalho">
    <a href="https://speech.fish.audio" title="Fish Audio" class="md-header__button md-logo" aria-label="Fish Audio" data-md-component="logo">
      
  <img src="../../assets/logo.svg" alt="logo">

    </a>
    <label class="md-header__button md-icon" for="__drawer">
      
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
    </label>
    <div class="md-header__title" data-md-component="header-title">
      <div class="md-header__ellipsis">
        <div class="md-header__topic">
          <span class="md-ellipsis">
            Fish Audio
          </span>
        </div>
        <div class="md-header__topic" data-md-component="header-topic">
          <span class="md-ellipsis">
            
              Ajuste Fino
            
          </span>
        </div>
      </div>
    </div>
    
      
        <form class="md-header__option" data-md-component="palette">
  
    
    <input class="md-option" data-md-color-media="(prefers-color-scheme)" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo"  aria-label="Switch to light mode"  type="radio" name="__palette" id="__palette_0">
    
      <label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m14.3 16-.7-2h-3.2l-.7 2H7.8L11 7h2l3.2 9zM20 8.69V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12zm-9.15 3.96h2.3L12 9z"/></svg>
      </label>
    
  
    <input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="black" data-md-color-accent="indigo"  aria-label="Switch to dark mode"  type="radio" name="__palette" id="__palette_1">
    
      <label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
      </label>
    
  
    <input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="indigo"  aria-label="Switch to light mode"  type="radio" name="__palette" id="__palette_2">
    
      <label class="md-header__button md-icon" title="Switch to light mode" for="__palette_0" hidden>
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
      </label>
    
  
</form>
      
    
      <script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
    
    
      <div class="md-header__option">
  <div class="md-select">
    
    <button class="md-header__button md-icon" aria-label="Selecione o idioma">
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m12.87 15.07-2.54-2.51.03-.03A17.5 17.5 0 0 0 14.07 6H17V4h-7V2H8v2H1v2h11.17C11.5 7.92 10.44 9.75 9 11.35 8.07 10.32 7.3 9.19 6.69 8h-2c.73 1.63 1.73 3.17 2.98 4.56l-5.09 5.02L4 19l5-5 3.11 3.11zM18.5 10h-2L12 22h2l1.12-3h4.75L21 22h2zm-2.62 7 1.62-4.33L19.12 17z"/></svg>
    </button>
    <div class="md-select__inner">
      <ul class="md-select__list">
        
          <li class="md-select__item">
            <a href="../../finetune/" hreflang="en" class="md-select__link">
              English
            </a>
          </li>
        
          <li class="md-select__item">
            <a href="../../zh/finetune/" hreflang="zh" class="md-select__link">
              简体中文
            </a>
          </li>
        
          <li class="md-select__item">
            <a href="../../ja/finetune/" hreflang="ja" class="md-select__link">
              日本語
            </a>
          </li>
        
          <li class="md-select__item">
            <a href="./" hreflang="pt" class="md-select__link">
              Português (Brasil)
            </a>
          </li>
        
          <li class="md-select__item">
            <a href="../../ko/finetune/" hreflang="ko" class="md-select__link">
              한국어
            </a>
          </li>
        
          <li class="md-select__item">
            <a href="../../ar/finetune/" hreflang="ar" class="md-select__link">
              العربية
            </a>
          </li>
        
      </ul>
    </div>
  </div>
</div>
    
    
        <label class="md-header__button md-icon" for="__search">
          
          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
        </label>
        <div class="md-search" data-md-component="search" role="dialog">
  <label class="md-search__overlay" for="__search"></label>
  <div class="md-search__inner" role="search">
    <form class="md-search__form" name="search">
      <input type="text" class="md-search__input" name="query" aria-label="Buscar" placeholder="Buscar" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
      <label class="md-search__icon md-icon" for="__search">
        
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
        
        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
      </label>
      <nav class="md-search__options" aria-label="Pesquisar">
        
          <a href="javascript:void(0)" class="md-search__icon md-icon" title="Compartilhar" aria-label="Compartilhar" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
            
            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
          </a>
        
        <button type="reset" class="md-search__icon md-icon" title="Limpar" aria-label="Limpar" tabindex="-1">
          
          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
        </button>
      </nav>
      
        <div class="md-search__suggest" data-md-component="search-suggest"></div>
      
    </form>
    <div class="md-search__output">
      <div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
        <div class="md-search-result" data-md-component="search-result">
          <div class="md-search-result__meta">
            Inicializando a pesquisa
          </div>
          <ol class="md-search-result__list" role="presentation"></ol>
        </div>
      </div>
    </div>
  </div>
</div>
      
    
      <div class="md-header__source">
        <a href="https://github.com/fishaudio/fish-speech" title="Ir ao repositório" class="md-source" data-md-component="source">
  <div class="md-source__icon md-icon">
    
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
  </div>
  <div class="md-source__repository">
    fishaudio/fish-speech
  </div>
</a>
      </div>
    
  </nav>
  
</header>
    
    <div class="md-container" data-md-component="container">
      
      
      <main class="md-main" data-md-component="main">
        <div class="md-main__inner md-grid">
          
            
              <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
                <div class="md-sidebar__scrollwrap">
                  <div class="md-sidebar__inner">
                    

<nav class="md-nav md-nav--primary" aria-label="Navegação" data-md-level="0">
  <label class="md-nav__title" for="__drawer">
    <a href="https://speech.fish.audio" title="Fish Audio" class="md-nav__button md-logo" aria-label="Fish Audio" data-md-component="logo">
      
  <img src="../../assets/logo.svg" alt="logo">

    </a>
    Fish Audio
  </label>
  
    <div class="md-nav__source">
      <a href="https://github.com/fishaudio/fish-speech" title="Ir ao repositório" class="md-source" data-md-component="source">
  <div class="md-source__icon md-icon">
    
    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
  </div>
  <div class="md-source__repository">
    fishaudio/fish-speech
  </div>
</a>
    </div>
  
  <ul class="md-nav__list" data-md-scrollfix>
    
      
    <li class="md-nav__item">
      <a href="../" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    
  
    Introdução
  

  </span>
  
  
      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../install/" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    
  
    Instalação
  

  </span>
  
  
      </a>
    </li>
  

    <li class="md-nav__item md-nav__item--active">
      
      <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
      
      
        <label class="md-nav__link md-nav__link--active" for="__toc">
          
  
  <span class="md-ellipsis">
    
  
    Ajuste Fino
  

  </span>
  
  
          <span class="md-nav__icon md-icon"></span>
        </label>
      
      <a href="./" class="md-nav__link md-nav__link--active">
        
  
  <span class="md-ellipsis">
    
  
    Ajuste Fino
  

  </span>
  
  
      </a>
      
        
<nav class="md-nav md-nav--secondary" aria-label="Índice">
  
  
    <label class="md-nav__title" for="__toc">
      <span class="md-nav__icon md-icon"></span>
      Índice
    </label>
    <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
      
        <li class="md-nav__item">
  <a href="#ajuste-fino-do-llama" class="md-nav__link">
    <span class="md-ellipsis">
      
        Ajuste Fino do LLAMA
      
    </span>
  </a>
  
    <nav class="md-nav" aria-label="Ajuste Fino do LLAMA">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1-prepare-o-conjunto-de-dados" class="md-nav__link">
    <span class="md-ellipsis">
      
        1. Prepare o conjunto de dados
      
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2-extracao-em-lote-de-tokens-semanticos" class="md-nav__link">
    <span class="md-ellipsis">
      
        2. Extração em lote de tokens semânticos
      
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3-empacote-o-conjunto-de-dados-em-protobuf" class="md-nav__link">
    <span class="md-ellipsis">
      
        3. Empacote o conjunto de dados em protobuf
      
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4-finalmente-ajuste-fino-com-lora" class="md-nav__link">
    <span class="md-ellipsis">
      
        4. Finalmente, ajuste fino com LoRA
      
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
    </ul>
  
</nav>
      
    </li>
  

    <li class="md-nav__item">
      <a href="../inference/" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    
  
    Inferência
  

  </span>
  
  
      </a>
    </li>
  

    <li class="md-nav__item">
      <a href="../samples.md" class="md-nav__link">
        
  
  <span class="md-ellipsis">
    
  
    Amostras
  

  </span>
  
  
      </a>
    </li>
  

  </ul>
</nav>
                  </div>
                </div>
              </div>
            
            
              <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
                <div class="md-sidebar__scrollwrap">
                  <div class="md-sidebar__inner">
                    

<nav class="md-nav md-nav--secondary" aria-label="Índice">
  
  
    <label class="md-nav__title" for="__toc">
      <span class="md-nav__icon md-icon"></span>
      Índice
    </label>
    <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
      
        <li class="md-nav__item">
  <a href="#ajuste-fino-do-llama" class="md-nav__link">
    <span class="md-ellipsis">
      
        Ajuste Fino do LLAMA
      
    </span>
  </a>
  
    <nav class="md-nav" aria-label="Ajuste Fino do LLAMA">
      <ul class="md-nav__list">
        
          <li class="md-nav__item">
  <a href="#1-prepare-o-conjunto-de-dados" class="md-nav__link">
    <span class="md-ellipsis">
      
        1. Prepare o conjunto de dados
      
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#2-extracao-em-lote-de-tokens-semanticos" class="md-nav__link">
    <span class="md-ellipsis">
      
        2. Extração em lote de tokens semânticos
      
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#3-empacote-o-conjunto-de-dados-em-protobuf" class="md-nav__link">
    <span class="md-ellipsis">
      
        3. Empacote o conjunto de dados em protobuf
      
    </span>
  </a>
  
</li>
        
          <li class="md-nav__item">
  <a href="#4-finalmente-ajuste-fino-com-lora" class="md-nav__link">
    <span class="md-ellipsis">
      
        4. Finalmente, ajuste fino com LoRA
      
    </span>
  </a>
  
</li>
        
      </ul>
    </nav>
  
</li>
      
    </ul>
  
</nav>
                  </div>
                </div>
              </div>
            
          
            <div class="md-content" data-md-component="content">
              
              <article class="md-content__inner md-typeset">
                
                  
    <a href="https://github.com/fishaudio/fish-speech/blob/main/docs/pt/finetune.md" title="Editar esta página" class="md-content__button md-icon" rel="edit">
      
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M10 20H6V4h7v5h5v3.1l2-2V8l-6-6H6c-1.1 0-2 .9-2 2v16c0 1.1.9 2 2 2h4zm10.2-7c.1 0 .3.1.4.2l1.3 1.3c.2.2.2.6 0 .8l-1 1-2.1-2.1 1-1c.1-.1.2-.2.4-.2m0 3.9L14.1 23H12v-2.1l6.1-6.1z"/></svg>
    </a>
  
  
    <a href="https://github.com/fishaudio/fish-speech/raw/main/docs/pt/finetune.md" title="Ver fonte desta página" class="md-content__button md-icon">
      
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M17 18c.56 0 1 .44 1 1s-.44 1-1 1-1-.44-1-1 .44-1 1-1m0-3c-2.73 0-5.06 1.66-6 4 .94 2.34 3.27 4 6 4s5.06-1.66 6-4c-.94-2.34-3.27-4-6-4m0 6.5a2.5 2.5 0 0 1-2.5-2.5 2.5 2.5 0 0 1 2.5-2.5 2.5 2.5 0 0 1 2.5 2.5 2.5 2.5 0 0 1-2.5 2.5M9.27 20H6V4h7v5h5v4.07c.7.08 1.36.25 2 .49V8l-6-6H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h4.5a8.2 8.2 0 0 1-1.23-2"/></svg>
    </a>
  

<h1 id="ajuste-fino-fine-tuning">Ajuste Fino (Fine-tuning)</h1>
<p>Obviamente, ao abrir esta página, você não estava satisfeito com o desempenho do modelo pré-treinado em modo zero-shot. Você deseja fazer um ajuste fino em um modelo para melhorar seu desempenho em seu conjunto de dados.</p>
<p>Na versão atual, você só precisa fazer o ajuste fino da parte 'LLAMA'.</p>
<h2 id="ajuste-fino-do-llama">Ajuste Fino do LLAMA</h2>
<h3 id="1-prepare-o-conjunto-de-dados">1. Prepare o conjunto de dados</h3>
<div class="language-text highlight"><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>.
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>├── SPK1
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a>│   ├── 21.15-26.44.lab
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a>│   ├── 21.15-26.44.mp3
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a>│   ├── 27.51-29.98.lab
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a>│   ├── 27.51-29.98.mp3
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a>│   ├── 30.1-32.71.lab
</span><span id="__span-0-8"><a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a>│   └── 30.1-32.71.mp3
</span><span id="__span-0-9"><a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a>└── SPK2
</span><span id="__span-0-10"><a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a>    ├── 38.79-40.85.lab
</span><span id="__span-0-11"><a id="__codelineno-0-11" name="__codelineno-0-11" href="#__codelineno-0-11"></a>    └── 38.79-40.85.mp3
</span></code></pre></div>
<p>Você precisa converter seu conjunto de dados para o formato acima e colocá-lo no diretório <code>data</code>. O arquivo de áudio pode ter as extensões <code>.mp3</code>, <code>.wav</code> ou <code>.flac</code>, e o arquivo de anotação deve ter a extensão <code>.lab</code>.</p>
<div class="admonition info">
<p class="admonition-title">Info</p>
<p>O arquivo de anotação <code>.lab</code> precisa conter apenas a transcrição do áudio, sem necessidade de formatação especial. Por exemplo, se <code>hi.mp3</code> contiver "Olá, adeus.", então o arquivo <code>hi.lab</code> conterá uma única linha de texto: "Olá, adeus.".</p>
</div>
<div class="admonition warning">
<p class="admonition-title">Warning</p>
<p>Recomenda-se aplicar a normalização de volume (loudness) ao conjunto de dados. Você pode usar o <a href="https://github.com/fishaudio/audio-preprocess">fish-audio-preprocess</a> para fazer isso.
<div class="language-bash highlight"><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a>fap<span class="w"> </span>loudness-norm<span class="w"> </span>data-raw<span class="w"> </span>data<span class="w"> </span>--clean
</span></code></pre></div></p>
</div>
<h3 id="2-extracao-em-lote-de-tokens-semanticos">2. Extração em lote de tokens semânticos</h3>
<p>Certifique-se de que você baixou os pesos do VQGAN. Se não, execute o seguinte comando:</p>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-2-1"><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a>huggingface-cli<span class="w"> </span>download<span class="w"> </span>fishaudio/openaudio-s1-mini<span class="w"> </span>--local-dir<span class="w"> </span>checkpoints/openaudio-s1-mini
</span></code></pre></div>
<p>Em seguida, você pode executar o seguinte comando para extrair os tokens semânticos:</p>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-3-1"><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a>python<span class="w"> </span>tools/vqgan/extract_vq.py<span class="w"> </span>data<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-2"><a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a><span class="w">    </span>--num-workers<span class="w"> </span><span class="m">1</span><span class="w"> </span>--batch-size<span class="w"> </span><span class="m">16</span><span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-3"><a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a><span class="w">    </span>--config-name<span class="w"> </span><span class="s2">&quot;modded_dac_vq&quot;</span><span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-4"><a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a><span class="w">    </span>--checkpoint-path<span class="w"> </span><span class="s2">&quot;checkpoints/openaudio-s1-mini/codec.pth&quot;</span>
</span></code></pre></div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Você pode ajustar <code>--num-workers</code> e <code>--batch-size</code> para aumentar a velocidade de extração, mas certifique-se de não exceder o limite de memória da sua GPU.</p>
</div>
<p>Este comando criará arquivos <code>.npy</code> no diretório <code>data</code>, como mostrado abaixo:</p>
<div class="language-text highlight"><pre><span></span><code><span id="__span-4-1"><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a>.
</span><span id="__span-4-2"><a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a>├── SPK1
</span><span id="__span-4-3"><a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a>│   ├── 21.15-26.44.lab
</span><span id="__span-4-4"><a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a>│   ├── 21.15-26.44.mp3
</span><span id="__span-4-5"><a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a>│   ├── 21.15-26.44.npy
</span><span id="__span-4-6"><a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a>│   ├── 27.51-29.98.lab
</span><span id="__span-4-7"><a id="__codelineno-4-7" name="__codelineno-4-7" href="#__codelineno-4-7"></a>│   ├── 27.51-29.98.mp3
</span><span id="__span-4-8"><a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a>│   ├── 27.51-29.98.npy
</span><span id="__span-4-9"><a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a>│   ├── 30.1-32.71.lab
</span><span id="__span-4-10"><a id="__codelineno-4-10" name="__codelineno-4-10" href="#__codelineno-4-10"></a>│   ├── 30.1-32.71.mp3
</span><span id="__span-4-11"><a id="__codelineno-4-11" name="__codelineno-4-11" href="#__codelineno-4-11"></a>│   └── 30.1-32.71.npy
</span><span id="__span-4-12"><a id="__codelineno-4-12" name="__codelineno-4-12" href="#__codelineno-4-12"></a>└── SPK2
</span><span id="__span-4-13"><a id="__codelineno-4-13" name="__codelineno-4-13" href="#__codelineno-4-13"></a>    ├── 38.79-40.85.lab
</span><span id="__span-4-14"><a id="__codelineno-4-14" name="__codelineno-4-14" href="#__codelineno-4-14"></a>    ├── 38.79-40.85.mp3
</span><span id="__span-4-15"><a id="__codelineno-4-15" name="__codelineno-4-15" href="#__codelineno-4-15"></a>    └── 38.79-40.85.npy
</span></code></pre></div>
<h3 id="3-empacote-o-conjunto-de-dados-em-protobuf">3. Empacote o conjunto de dados em protobuf</h3>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-5-1"><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a>python<span class="w"> </span>tools/llama/build_dataset.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-5-2"><a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="w">    </span>--input<span class="w"> </span><span class="s2">&quot;data&quot;</span><span class="w"> </span><span class="se">\</span>
</span><span id="__span-5-3"><a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="w">    </span>--output<span class="w"> </span><span class="s2">&quot;data/protos&quot;</span><span class="w"> </span><span class="se">\</span>
</span><span id="__span-5-4"><a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="w">    </span>--text-extension<span class="w"> </span>.lab<span class="w"> </span><span class="se">\</span>
</span><span id="__span-5-5"><a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="w">    </span>--num-workers<span class="w"> </span><span class="m">16</span>
</span></code></pre></div>
<p>Após a conclusão da execução do comando, você deverá ver o arquivo <code>protos</code> no diretório <code>data</code>.</p>
<h3 id="4-finalmente-ajuste-fino-com-lora">4. Finalmente, ajuste fino com LoRA</h3>
<p>Da mesma forma, certifique-se de que você baixou os pesos do <code>LLAMA</code>. Se não, execute o seguinte comando:</p>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-6-1"><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a>huggingface-cli<span class="w"> </span>download<span class="w"> </span>fishaudio/openaudio-s1-mini<span class="w"> </span>--local-dir<span class="w"> </span>checkpoints/openaudio-s1-mini
</span></code></pre></div>
<p>Finalmente, você pode iniciar o ajuste fino executando o seguinte comando:</p>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-7-1"><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a>python<span class="w"> </span>fish_speech/train.py<span class="w"> </span>--config-name<span class="w"> </span>text2semantic_finetune<span class="w"> </span><span class="se">\</span>
</span><span id="__span-7-2"><a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a><span class="w">    </span><span class="nv">project</span><span class="o">=</span><span class="nv">$project</span><span class="w"> </span><span class="se">\</span>
</span><span id="__span-7-3"><a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a><span class="w">    </span>+lora@model.model.lora_config<span class="o">=</span>r_8_alpha_16
</span></code></pre></div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Você pode modificar os parâmetros de treinamento, como <code>batch_size</code>, <code>gradient_accumulation_steps</code>, etc., para se adequar à memória da sua GPU, modificando <code>fish_speech/configs/text2semantic_finetune.yaml</code>.</p>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Para usuários do Windows, você pode usar <code>trainer.strategy.process_group_backend=gloo</code> para evitar problemas com <code>nccl</code>.</p>
</div>
<p>Após o treinamento ser concluído, você pode consultar a seção de <a href="../inference/">inferência</a> para testar seu modelo.</p>
<div class="admonition info">
<p class="admonition-title">Info</p>
<p>Por padrão, o modelo aprenderá apenas os padrões de fala do locutor e não o timbre. Você ainda precisará usar prompts para garantir a estabilidade do timbre.
Se você quiser aprender o timbre, pode aumentar o número de passos de treinamento, mas isso pode levar a um sobreajuste (overfitting).</p>
</div>
<p>Após o treinamento, você precisa converter os pesos do LoRA para pesos regulares antes de realizar a inferência.</p>
<p><code>bash
python tools/llama/merge_lora.py \
    --lora-config r_8_alpha_16 \
    --base-weight checkpoints/openaudio-s1-mini \
    --lora-weight results/$project/checkpoints/step_000000010.ckpt \
    --output checkpoints/openaudio-s1-mini-yth-lora/</code></p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Você também pode tentar outros checkpoints. Sugerimos usar o checkpoint mais antigo que atenda aos seus requisitos, pois eles geralmente têm um desempenho melhor em dados fora de distribuição (OOD).</p>
</div>


              </article>
            </div>
          
          
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
        </div>
        
      </main>
      
        <footer class="md-footer">
  
    
      <nav class="md-footer__inner md-grid" aria-label="Rodapé" >
        
          
          <a href="../install/" class="md-footer__link md-footer__link--prev" aria-label="Anterior: Instalação">
            <div class="md-footer__button md-icon">
              
              <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
            </div>
            <div class="md-footer__title">
              <span class="md-footer__direction">
                Anterior
              </span>
              <div class="md-ellipsis">
                Instalação
              </div>
            </div>
          </a>
        
        
          <a href="../inference/" class="md-footer__link md-footer__link--next" aria-label="Próximo: Inferência">
            <div class="md-footer__title">
              <span class="md-footer__direction">
                Próximo
              </span>
              <div class="md-ellipsis">
                Inferência
              </div>
            </div>
            <div class="md-footer__button md-icon">
              
              <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11z"/></svg>
            </div>
          </a>
        
      </nav>
    
  
  <div class="md-footer-meta md-typeset">
    <div class="md-footer-meta__inner md-grid">
      <div class="md-copyright">
  
    <div class="md-copyright__highlight">
      Copyright &copy; 2023-2025 by Fish Audio
    </div>
  
  
    Made with
    <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
      Material for MkDocs
    </a>
  
</div>
      
        
<div class="md-social">
  
    
    <a href="https://discord.gg/Es5qTB9BcN" target="_blank" rel="noopener" title="discord.gg" class="md-social__link">
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M492.5 69.8c-.2-.3-.4-.6-.8-.7-38.1-17.5-78.4-30-119.7-37.1-.4-.1-.8 0-1.1.1s-.6.4-.8.8c-5.5 9.9-10.5 20.2-14.9 30.6-44.6-6.8-89.9-6.8-134.4 0-4.5-10.5-9.5-20.7-15.1-30.6-.2-.3-.5-.6-.8-.8s-.7-.2-1.1-.2C162.5 39 122.2 51.5 84.1 69c-.3.1-.6.4-.8.7C7.1 183.5-13.8 294.6-3.6 404.2c0 .3.1.5.2.8s.3.4.5.6c44.4 32.9 94 58 146.8 74.2.4.1.8.1 1.1 0s.7-.4.9-.7c11.3-15.4 21.4-31.8 30-48.8.1-.2.2-.5.2-.8s0-.5-.1-.8-.2-.5-.4-.6-.4-.3-.7-.4c-15.8-6.1-31.2-13.4-45.9-21.9-.3-.2-.5-.4-.7-.6s-.3-.6-.3-.9 0-.6.2-.9.3-.5.6-.7c3.1-2.3 6.2-4.7 9.1-7.1.3-.2.6-.4.9-.4s.7 0 1 .1c96.2 43.9 200.4 43.9 295.5 0 .3-.1.7-.2 1-.2s.7.2.9.4c2.9 2.4 6 4.9 9.1 7.2.2.2.4.4.6.7s.2.6.2.9-.1.6-.3.9-.4.5-.6.6c-14.7 8.6-30 15.9-45.9 21.8-.2.1-.5.2-.7.4s-.3.4-.4.7-.1.5-.1.8.1.5.2.8c8.8 17 18.8 33.3 30 48.8.2.3.6.6.9.7s.8.1 1.1 0c52.9-16.2 102.6-41.3 147.1-74.2.2-.2.4-.4.5-.6s.2-.5.2-.8c12.3-126.8-20.5-236.9-86.9-334.5zm-302 267.7c-29 0-52.8-26.6-52.8-59.2s23.4-59.2 52.8-59.2c29.7 0 53.3 26.8 52.8 59.2 0 32.7-23.4 59.2-52.8 59.2m195.4 0c-29 0-52.8-26.6-52.8-59.2s23.4-59.2 52.8-59.2c29.7 0 53.3 26.8 52.8 59.2 0 32.7-23.2 59.2-52.8 59.2"/></svg>
    </a>
  
    
    <a href="https://hub.docker.com/r/fishaudio/fish-speech" target="_blank" rel="noopener" title="hub.docker.com" class="md-social__link">
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M349.9 236.3h-66.1v-59.4h66.1zm0-204.3h-66.1v60.7h66.1zm78.2 144.8H362v59.4h66.1zm-156.3-72.1h-66.1v60.1h66.1zm78.1 0h-66.1v60.1h66.1zm276.8 100c-14.4-9.7-47.6-13.2-73.1-8.4-3.3-24-16.7-44.9-41.1-63.7l-14-9.3-9.3 14c-18.4 27.8-23.4 73.6-3.7 103.8-8.7 4.7-25.8 11.1-48.4 10.7H2.4c-8.7 50.8 5.8 116.8 44 162.1 37.1 43.9 92.7 66.2 165.4 66.2 157.4 0 273.9-72.5 328.4-204.2 21.4.4 67.6.1 91.3-45.2 1.5-2.5 6.6-13.2 8.5-17.1zm-511.1-27.9h-66v59.4h66.1v-59.4zm78.1 0h-66.1v59.4h66.1zm78.1 0h-66.1v59.4h66.1zm-78.1-72.1h-66.1v60.1h66.1z"/></svg>
    </a>
  
    
    <a href="http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=jCKlUP7QgSm9kh95UlBoYv6s1I-Apl1M&authKey=xI5ttVAp3do68IpEYEalwXSYZFdfxZSkah%2BctF5FIMyN2NqAa003vFtLqJyAVRfF&noverify=0&group_code=593946093" target="_blank" rel="noopener" title="qm.qq.com" class="md-social__link">
      <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M434.1 420.4c-11.5 1.4-44.9-52.7-44.9-52.7 0 31.3-16.1 72.2-51 101.8 16.8 5.2 54.8 19.2 45.8 34.4-7.3 12.3-125.5 7.9-159.6 4-34.1 3.8-152.3 8.3-159.6-4-9-15.2 28.9-29.2 45.8-34.4-34.9-29.5-51.1-70.4-51.1-101.8 0 0-33.3 54.1-44.9 52.7-5.4-.6-12.4-29.6 9.3-99.7 10.3-33 22-60.5 40.1-105.8C60.9 98 109.2-.1 224.3-.1 338-.1 387.5 96 384.6 214.9c18.1 45.2 29.9 72.9 40.1 105.8 21.8 70.1 14.7 99.1 9.3 99.7z"/></svg>
    </a>
  
</div>
      
    </div>
  </div>
</footer>
      
    </div>
    <div class="md-dialog" data-md-component="dialog">
      <div class="md-dialog__inner md-typeset"></div>
    </div>
    
    
      <script id="__config" type="application/json">{"annotate": null, "base": "../..", "features": ["content.action.edit", "content.action.view", "navigation.tracking", "navigation.footer", "search", "search.suggest", "search.highlight", "search.share", "content.code.copy"], "search": "../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copiado para \u00e1rea de transfer\u00eancia", "clipboard.copy": "Copiar para \u00e1rea de transfer\u00eancia", "search.result.more.one": "Mais 1 nesta p\u00e1gina", "search.result.more.other": "Mais # nesta p\u00e1gina", "search.result.none": "Nenhum resultado encontrado", "search.result.one": "1 resultado encontrado", "search.result.other": "# resultados encontrados", "search.result.placeholder": "Digite para iniciar a busca", "search.result.term.missing": "Ausente", "select.version": "Selecione a vers\u00e3o"}, "version": null}</script>
    
    
      <script src="../../assets/javascripts/bundle.79ae519e.min.js"></script>
      
    
  </body>
</html>