| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301 |
- <!doctype html>
- <html lang="zh" 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/zh/">
-
-
-
- <link rel="next" href="install/">
-
-
-
- <link rel="alternate" href="/" hreflang="en">
-
- <link rel="alternate" href="/zh/" hreflang="zh">
-
- <link rel="alternate" href="/ja/" hreflang="ja">
-
- <link rel="alternate" href="/pt/" hreflang="pt">
-
- <link rel="alternate" href="/ko/" hreflang="ko">
-
- <link rel="alternate" href="/ar/" hreflang="ar">
-
-
-
- <link rel="icon" href="../assets/logo.svg">
- <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.1">
-
-
-
- <title>介绍 - 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="#_1" class="md-skip">
- 跳转至
- </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="页眉">
- <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">
-
- 介绍
-
- </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="选择当前语言">
- <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="/" hreflang="en" class="md-select__link">
- English
- </a>
- </li>
-
- <li class="md-select__item">
- <a href="/zh/" hreflang="zh" class="md-select__link">
- 简体中文
- </a>
- </li>
-
- <li class="md-select__item">
- <a href="/ja/" hreflang="ja" class="md-select__link">
- 日本語
- </a>
- </li>
-
- <li class="md-select__item">
- <a href="/pt/" hreflang="pt" class="md-select__link">
- Português (Brasil)
- </a>
- </li>
-
- <li class="md-select__item">
- <a href="/ko/" hreflang="ko" class="md-select__link">
- 한국어
- </a>
- </li>
-
- <li class="md-select__item">
- <a href="/ar/" 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="搜索" placeholder="搜索" 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="查找">
-
- <a href="javascript:void(0)" class="md-search__icon md-icon" title="分享" aria-label="分享" 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="清空当前内容" aria-label="清空当前内容" 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">
- 正在初始化搜索引擎
- </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="前往仓库" 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="导航栏" 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="前往仓库" 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 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">
-
-
- 介绍
-
-
- </span>
-
-
- <span class="md-nav__icon md-icon"></span>
- </label>
-
- <a href="./" class="md-nav__link md-nav__link--active">
-
-
-
- <span class="md-ellipsis">
-
-
- 介绍
-
-
- </span>
-
-
- </a>
-
-
- <nav class="md-nav md-nav--secondary" aria-label="目录">
-
-
-
-
- <label class="md-nav__title" for="__toc">
- <span class="md-nav__icon md-icon"></span>
- 目录
- </label>
- <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
-
- <li class="md-nav__item">
- <a href="#_1" class="md-nav__link">
- <span class="md-ellipsis">
-
- 快速开始
-
- </span>
- </a>
-
- <nav class="md-nav" aria-label="快速开始">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#_2" class="md-nav__link">
- <span class="md-ellipsis">
-
- 文档入口
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#llm-agent" class="md-nav__link">
- <span class="md-ellipsis">
-
- LLM Agent 指南
-
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#fish-audio-s2" class="md-nav__link">
- <span class="md-ellipsis">
-
- Fish Audio S2
-
- </span>
- </a>
-
- <nav class="md-nav" aria-label="Fish Audio S2">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#_3" class="md-nav__link">
- <span class="md-ellipsis">
-
- 模型变体
-
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_4" class="md-nav__link">
- <span class="md-ellipsis">
-
- 基准测试结果
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_5" class="md-nav__link">
- <span class="md-ellipsis">
-
- 亮点
-
- </span>
- </a>
-
- <nav class="md-nav" aria-label="亮点">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#_6" class="md-nav__link">
- <span class="md-ellipsis">
-
- 通过自然语言进行细粒度行内控制
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#dual-autoregressive" class="md-nav__link">
- <span class="md-ellipsis">
-
- 双自回归架构(Dual-Autoregressive)
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_7" class="md-nav__link">
- <span class="md-ellipsis">
-
- 强化学习对齐
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#sglang" class="md-nav__link">
- <span class="md-ellipsis">
-
- 基于 SGLang 的生产级流式推理
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_8" class="md-nav__link">
- <span class="md-ellipsis">
-
- 多语言支持
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_9" class="md-nav__link">
- <span class="md-ellipsis">
-
- 原生多说话人生成
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_10" class="md-nav__link">
- <span class="md-ellipsis">
-
- 多轮对话生成
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_11" class="md-nav__link">
- <span class="md-ellipsis">
-
- 快速语音克隆
-
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_12" class="md-nav__link">
- <span class="md-ellipsis">
-
- 致谢
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_13" class="md-nav__link">
- <span class="md-ellipsis">
-
- 技术报告
-
- </span>
- </a>
-
- </li>
-
- </ul>
-
- </nav>
-
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="install/" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
-
-
- 安装
-
-
- </span>
-
-
- </a>
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="finetune/" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
-
-
- 微调
-
-
- </span>
-
-
- </a>
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="inference/" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
-
-
- 推理
-
-
- </span>
-
-
- </a>
- </li>
-
-
-
-
-
-
-
-
- <li class="md-nav__item">
- <a href="samples.md" class="md-nav__link">
-
-
-
- <span class="md-ellipsis">
-
-
- 示例
-
-
- </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="目录">
-
-
-
-
- <label class="md-nav__title" for="__toc">
- <span class="md-nav__icon md-icon"></span>
- 目录
- </label>
- <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
-
- <li class="md-nav__item">
- <a href="#_1" class="md-nav__link">
- <span class="md-ellipsis">
-
- 快速开始
-
- </span>
- </a>
-
- <nav class="md-nav" aria-label="快速开始">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#_2" class="md-nav__link">
- <span class="md-ellipsis">
-
- 文档入口
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#llm-agent" class="md-nav__link">
- <span class="md-ellipsis">
-
- LLM Agent 指南
-
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#fish-audio-s2" class="md-nav__link">
- <span class="md-ellipsis">
-
- Fish Audio S2
-
- </span>
- </a>
-
- <nav class="md-nav" aria-label="Fish Audio S2">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#_3" class="md-nav__link">
- <span class="md-ellipsis">
-
- 模型变体
-
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_4" class="md-nav__link">
- <span class="md-ellipsis">
-
- 基准测试结果
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_5" class="md-nav__link">
- <span class="md-ellipsis">
-
- 亮点
-
- </span>
- </a>
-
- <nav class="md-nav" aria-label="亮点">
- <ul class="md-nav__list">
-
- <li class="md-nav__item">
- <a href="#_6" class="md-nav__link">
- <span class="md-ellipsis">
-
- 通过自然语言进行细粒度行内控制
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#dual-autoregressive" class="md-nav__link">
- <span class="md-ellipsis">
-
- 双自回归架构(Dual-Autoregressive)
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_7" class="md-nav__link">
- <span class="md-ellipsis">
-
- 强化学习对齐
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#sglang" class="md-nav__link">
- <span class="md-ellipsis">
-
- 基于 SGLang 的生产级流式推理
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_8" class="md-nav__link">
- <span class="md-ellipsis">
-
- 多语言支持
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_9" class="md-nav__link">
- <span class="md-ellipsis">
-
- 原生多说话人生成
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_10" class="md-nav__link">
- <span class="md-ellipsis">
-
- 多轮对话生成
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_11" class="md-nav__link">
- <span class="md-ellipsis">
-
- 快速语音克隆
-
- </span>
- </a>
-
- </li>
-
- </ul>
- </nav>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_12" class="md-nav__link">
- <span class="md-ellipsis">
-
- 致谢
-
- </span>
- </a>
-
- </li>
-
- <li class="md-nav__item">
- <a href="#_13" class="md-nav__link">
- <span class="md-ellipsis">
-
- 技术报告
-
- </span>
- </a>
-
- </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/zh/index.md" title="编辑此页" 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/zh/index.md" title="查看本页的源代码" 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>
-
- <div align="center">
- <h1>Fish Speech</h1>
- <p><a href="../en/">English</a> | <strong>简体中文</strong> | <a href="../pt/">Portuguese</a> | <a href="../ja/">日本語</a> | <a href="../ko/">한국어</a> | <a href="../ar/">العربية</a> | <a href="../es/">Español</a></p>
- <a href="https://www.producthunt.com/products/fish-speech?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_source=badge-fish-audio-s1" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=1023740&theme=light&period=daily&t=1761164814710" alt="Fish Audio S1 - Expressive Voice Cloning and Text-to-Speech | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
- <a href="https://trendshift.io/repositories/7014" target="_blank">
- <img src="https://trendshift.io/api/badge/repositories/7014" alt="fishaudio%2Ffish-speech | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
- </a>
- </div>
- <p><br></p>
- <div align="center">
- <img src="https://count.getloli.com/get/@fish-speech?theme=asoul" /><br>
- </div>
- <p><br></p>
- <div align="center">
- <a target="_blank" href="https://discord.gg/Es5qTB9BcN">
- <img alt="Discord" src="https://img.shields.io/discord/1214047546020728892?color=%23738ADB&label=Discord&logo=discord&logoColor=white&style=flat-square"/>
- </a>
- <a target="_blank" href="https://hub.docker.com/r/fishaudio/fish-speech">
- <img alt="Docker" src="https://img.shields.io/docker/pulls/fishaudio/fish-speech?style=flat-square&logo=docker"/>
- </a>
- <a target="_blank" href="https://pd.qq.com/s/bwxia254o">
- <img alt="QQ Channel" src="https://img.shields.io/badge/QQ-blue?logo=tencentqq">
- </a>
- </div>
- <div align="center">
- <a target="_blank" href="https://huggingface.co/fishaudio/s2">
- <img alt="HuggingFace Model" src="https://img.shields.io/badge/🤗%20-models-orange"/>
- </a>
- <a target="_blank" href="https://fish.audio/blog/fish-audio-open-sources-s2/">
- <img alt="Fish Audio Blog" src="https://img.shields.io/badge/Blog-Fish_Audio_S2-1f7a8c?style=flat-square&logo=readme&logoColor=white"/>
- </a>
- <a target="_blank" href="https://arxiv.org/abs/2603.08823">
- <img alt="Paper | Technical Report" src="https://img.shields.io/badge/Paper-Technical_Report-b31b1b?style=flat-square"/>
- </a>
- </div>
- <div class="admonition info">
- <p class="admonition-title">许可声明</p>
- <p>此代码库及其相关的模型权重均在 <strong>FISH AUDIO RESEARCH LICENSE</strong> 下发布。更多详情请参考 <a href="https://github.com/fishaudio/fish-speech/blob/main/LICENSE">LICENSE</a>。</p>
- </div>
- <div class="admonition warning">
- <p class="admonition-title">法律免责声明</p>
- <p>我们不对代码库的任何非法使用承担责任。请参考您当地关于 DMCA 和其他相关法律的法规。</p>
- </div>
- <h2 id="_1">快速开始</h2>
- <h3 id="_2">文档入口</h3>
- <p>这里是 Fish Audio S2 的官方文档,请按照说明轻松入门。</p>
- <ul>
- <li><a href="https://speech.fish.audio/zh/install/">安装</a></li>
- <li><a href="https://speech.fish.audio/zh/inference/">命令行推理</a></li>
- <li><a href="https://speech.fish.audio/zh/inference/">WebUI 推理</a></li>
- <li><a href="https://speech.fish.audio/zh/server/">服务端推理</a></li>
- <li><a href="https://speech.fish.audio/zh/install/">Docker 部署</a></li>
- </ul>
- <blockquote>
- <p>[!IMPORTANT]
- <strong>如需使用 SGLang Server,请参考 <a href="https://github.com/sgl-project/sglang-omni/blob/main/sglang_omni/models/fishaudio_s2_pro/README.md">SGLang-Omni README</a>。</strong></p>
- </blockquote>
- <h3 id="llm-agent">LLM Agent 指南</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>请先阅读 https://speech.fish.audio/zh/install/ ,并按文档安装和配置 Fish Audio S2。
- </span></code></pre></div>
- <h2 id="fish-audio-s2">Fish Audio S2</h2>
- <p><strong>在开源与闭源方案中都处于领先水平的文本转语音系统</strong></p>
- <p>Fish Audio S2 是由 <a href="https://fish.audio/">Fish Audio</a> 开发的最新模型。S2 在约 50 种语言、超过 1000 万小时音频数据上完成训练,并结合强化学习对齐与双自回归架构,能够生成自然、真实且情感丰富的语音。</p>
- <p>S2 支持通过自然语言标签(如 <code>[laugh]</code>、<code>[whispers]</code>、<code>[super happy]</code>)对韵律和情绪进行细粒度行内控制,同时原生支持多说话人和多轮生成。</p>
- <p>请访问 <a href="https://fish.audio/">Fish Audio 网站</a> 体验在线演示,并阅读<a href="https://fish.audio/blog/fish-audio-open-sources-s2/">博客文章</a>和<a href="https://arxiv.org/abs/2603.08823">技术报告</a>了解更多细节。</p>
- <h3 id="_3">模型变体</h3>
- <table>
- <thead>
- <tr>
- <th>模型</th>
- <th>大小</th>
- <th>可用性</th>
- <th>描述</th>
- </tr>
- </thead>
- <tbody>
- <tr>
- <td>S2-Pro</td>
- <td>4B 参数</td>
- <td><a href="https://huggingface.co/fishaudio/s2-pro">HuggingFace</a></td>
- <td>功能齐全的旗舰模型,具有最高质量和稳定性</td>
- </tr>
- </tbody>
- </table>
- <p>有关模型的更多详情,请参见<a href="https://arxiv.org/abs/2411.01156">技术报告</a>。</p>
- <h2 id="_4">基准测试结果</h2>
- <table>
- <thead>
- <tr>
- <th>基准</th>
- <th>Fish Audio S2</th>
- </tr>
- </thead>
- <tbody>
- <tr>
- <td>Seed-TTS Eval — WER(中文)</td>
- <td><strong>0.54%</strong>(总体最佳)</td>
- </tr>
- <tr>
- <td>Seed-TTS Eval — WER(英文)</td>
- <td><strong>0.99%</strong>(总体最佳)</td>
- </tr>
- <tr>
- <td>Audio Turing Test(含指令)</td>
- <td><strong>0.515</strong> 后验均值</td>
- </tr>
- <tr>
- <td>EmergentTTS-Eval — 胜率</td>
- <td><strong>81.88%</strong>(总体最高)</td>
- </tr>
- <tr>
- <td>Fish Instruction Benchmark — TAR</td>
- <td><strong>93.3%</strong></td>
- </tr>
- <tr>
- <td>Fish Instruction Benchmark — 质量</td>
- <td><strong>4.51 / 5.0</strong></td>
- </tr>
- <tr>
- <td>多语言(MiniMax Testset)— 最佳 WER</td>
- <td><strong>24</strong> 种语言中的 <strong>11</strong> 种</td>
- </tr>
- <tr>
- <td>多语言(MiniMax Testset)— 最佳 SIM</td>
- <td><strong>24</strong> 种语言中的 <strong>17</strong> 种</td>
- </tr>
- </tbody>
- </table>
- <p>在 Seed-TTS Eval 上,S2 在所有已评估模型(包括闭源系统)中实现了最低 WER:Qwen3-TTS(0.77/1.24)、MiniMax Speech-02(0.99/1.90)、Seed-TTS(1.12/2.25)。在 Audio Turing Test 上,S2 的 0.515 相比 Seed-TTS(0.417)提升 24%,相比 MiniMax-Speech(0.387)提升 33%。在 EmergentTTS-Eval 中,S2 在副语言学(91.61% 胜率)、疑问句(84.41%)和句法复杂度(83.39%)等维度表现尤为突出。</p>
- <h2 id="_5">亮点</h2>
- <p><img src="../assets/totalability.png" width=200%></p>
- <h3 id="_6">通过自然语言进行细粒度行内控制</h3>
- <p>Fish Audio S2 支持在文本中的特定词或短语位置直接嵌入自然语言指令,从而对语音生成进行局部控制。与依赖固定预设标签不同,S2 接受自由形式的文本描述,例如 [whisper in small voice]、[professional broadcast tone] 或 [pitch up],实现词级别的开放式表达控制。</p>
- <h3 id="dual-autoregressive">双自回归架构(Dual-Autoregressive)</h3>
- <p>S2 基于仅解码器 Transformer,并结合 RVQ 音频编解码器(10 个码本,约 21 Hz 帧率)。Dual-AR 架构将生成拆分为两个阶段:</p>
- <ul>
- <li><strong>Slow AR</strong> 沿时间轴运行,预测主语义码本。</li>
- <li><strong>Fast AR</strong> 在每个时间步生成剩余 9 个残差码本,用于重建细粒度声学细节。</li>
- </ul>
- <p>这种非对称设计(时间轴 4B 参数、深度轴 400M 参数)在保持音频保真度的同时,提高了推理效率。</p>
- <h3 id="_7">强化学习对齐</h3>
- <p>S2 使用 Group Relative Policy Optimization(GRPO)进行后训练对齐。用于过滤和标注训练数据的同一批模型被直接复用为 RL 的奖励模型,从而避免了预训练数据分布与后训练目标之间的不匹配。奖励信号综合了语义准确性、指令遵循、声学偏好评分与音色相似度。</p>
- <h3 id="sglang">基于 SGLang 的生产级流式推理</h3>
- <p>由于 Dual-AR 架构在结构上与标准自回归 LLM 同构,S2 可以直接继承 SGLang 提供的 LLM 原生服务优化能力,包括连续批处理、分页 KV Cache、CUDA Graph Replay 与基于 RadixAttention 的前缀缓存。</p>
- <p>在单张 NVIDIA H200 GPU 上:</p>
- <ul>
- <li><strong>实时因子(RTF):</strong> 0.195</li>
- <li><strong>首音频延迟:</strong> 约 100 ms</li>
- <li><strong>吞吐:</strong> 在 RTF 低于 0.5 的情况下达到 3,000+ acoustic tokens/s</li>
- </ul>
- <h3 id="_8">多语言支持</h3>
- <p>Fish Audio S2 支持高质量的多语言文本转语音,无需音素或特定语言的预处理。包括:</p>
- <p><strong>英语、中文、日语、韩语、阿拉伯语、德语、法语...</strong></p>
- <p><strong>以及更多!</strong></p>
- <p>列表正在不断扩大,请查看 <a href="https://fish.audio/">Fish Audio</a> 获取最新发布。</p>
- <h3 id="_9">原生多说话人生成</h3>
- <p><img src="../assets/chattemplate.png" width=200%></p>
- <p>Fish Audio S2 允许用户上传包含多个说话人的参考音频,模型将通过 <code><|speaker:i|></code> 令牌处理每个说话人的特征。之后您可以通过说话人 ID 令牌控制模型的表现,从而实现一次生成中包含多个说话人。再也不需要像以前那样针对每个说话人都单独上传参考音频与生成语音了。</p>
- <h3 id="_10">多轮对话生成</h3>
- <p>得益于模型上下文的扩展,我们的模型现在可以借助上文的信息提高后续生成内容的表现力,从而提升内容的自然度。</p>
- <h3 id="_11">快速语音克隆</h3>
- <p>Fish Audio S2 支持使用短参考样本(通常为 10-30 秒)进行准确的语音克隆。模型可以捕捉音色、说话风格和情感倾向,无需额外微调即可生成逼真且一致的克隆语音。
- 如需使用 SGLang Server,请参考 <a href="https://github.com/sgl-project/sglang-omni/blob/main/sglang_omni/models/fishaudio_s2_pro/README.md">SGLang-Omni README</a> 。</p>
- <hr />
- <h2 id="_12">致谢</h2>
- <ul>
- <li><a href="https://github.com/daniilrobnikov/vits2">VITS2 (daniilrobnikov)</a></li>
- <li><a href="https://github.com/fishaudio/Bert-VITS2">Bert-VITS2</a></li>
- <li><a href="https://github.com/innnky/gpt-vits">GPT VITS</a></li>
- <li><a href="https://github.com/b04901014/MQTTS">MQTTS</a></li>
- <li><a href="https://github.com/pytorch-labs/gpt-fast">GPT Fast</a></li>
- <li><a href="https://github.com/RVC-Boss/GPT-SoVITS">GPT-SoVITS</a></li>
- <li><a href="https://github.com/QwenLM/Qwen3">Qwen3</a></li>
- </ul>
- <h2 id="_13">技术报告</h2>
- <div class="language-bibtex highlight"><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a><span class="nc">@misc</span><span class="p">{</span><span class="nl">fish-speech-v1.4</span><span class="p">,</span>
- </span><span id="__span-1-2"><a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="w"> </span><span class="na">title</span><span class="p">=</span><span class="s">{Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis}</span><span class="p">,</span>
- </span><span id="__span-1-3"><a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a><span class="w"> </span><span class="na">author</span><span class="p">=</span><span class="s">{Shijia Liao and Yuxuan Wang and Tianyu Li and Yifan Cheng and Ruoyi Zhang and Rongzhi Zhou and Yijin Xing}</span><span class="p">,</span>
- </span><span id="__span-1-4"><a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a><span class="w"> </span><span class="na">year</span><span class="p">=</span><span class="s">{2024}</span><span class="p">,</span>
- </span><span id="__span-1-5"><a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a><span class="w"> </span><span class="na">eprint</span><span class="p">=</span><span class="s">{2411.01156}</span><span class="p">,</span>
- </span><span id="__span-1-6"><a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a><span class="w"> </span><span class="na">archivePrefix</span><span class="p">=</span><span class="s">{arXiv}</span><span class="p">,</span>
- </span><span id="__span-1-7"><a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a><span class="w"> </span><span class="na">primaryClass</span><span class="p">=</span><span class="s">{cs.SD}</span><span class="p">,</span>
- </span><span id="__span-1-8"><a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a><span class="w"> </span><span class="na">url</span><span class="p">=</span><span class="s">{https://arxiv.org/abs/2411.01156}</span><span class="p">,</span>
- </span><span id="__span-1-9"><a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a><span class="p">}</span>
- </span><span id="__span-1-10"><a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a>
- </span><span id="__span-1-11"><a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a><span class="nc">@misc</span><span class="p">{</span><span class="nl">liao2026fishaudios2technical</span><span class="p">,</span>
- </span><span id="__span-1-12"><a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a><span class="w"> </span><span class="na">title</span><span class="p">=</span><span class="s">{Fish Audio S2 Technical Report}</span><span class="p">,</span><span class="w"> </span>
- </span><span id="__span-1-13"><a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a><span class="w"> </span><span class="na">author</span><span class="p">=</span><span class="s">{Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han}</span><span class="p">,</span>
- </span><span id="__span-1-14"><a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a><span class="w"> </span><span class="na">year</span><span class="p">=</span><span class="s">{2026}</span><span class="p">,</span>
- </span><span id="__span-1-15"><a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a><span class="w"> </span><span class="na">eprint</span><span class="p">=</span><span class="s">{2603.08823}</span><span class="p">,</span>
- </span><span id="__span-1-16"><a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a><span class="w"> </span><span class="na">archivePrefix</span><span class="p">=</span><span class="s">{arXiv}</span><span class="p">,</span>
- </span><span id="__span-1-17"><a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a><span class="w"> </span><span class="na">primaryClass</span><span class="p">=</span><span class="s">{cs.SD}</span><span class="p">,</span>
- </span><span id="__span-1-18"><a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a><span class="w"> </span><span class="na">url</span><span class="p">=</span><span class="s">{https://arxiv.org/abs/2603.08823}</span><span class="p">,</span><span class="w"> </span>
- </span><span id="__span-1-19"><a id="__codelineno-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></a><span class="p">}</span>
- </span></code></pre></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="页脚" >
-
-
-
- <a href="install/" class="md-footer__link md-footer__link--next" aria-label="下一页: 安装">
- <div class="md-footer__title">
- <span class="md-footer__direction">
- 下一页
- </span>
- <div class="md-ellipsis">
- 安装
- </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 © 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": "\u5df2\u590d\u5236", "clipboard.copy": "\u590d\u5236", "search.result.more.one": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.more.other": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 # \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.none": "\u6ca1\u6709\u627e\u5230\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.one": "\u627e\u5230 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.other": "# \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.placeholder": "\u952e\u5165\u4ee5\u5f00\u59cb\u641c\u7d22", "search.result.term.missing": "\u7f3a\u5c11", "select.version": "\u9009\u62e9\u5f53\u524d\u7248\u672c"}, "version": null}</script>
-
-
- <script src="../assets/javascripts/bundle.79ae519e.min.js"></script>
-
-
- </body>
- </html>
|