mirrors / facebookresearch--audiocraft

项目文件夹

facebookresearch--audiocraft
文件
gh-docs
T
Alexandre Défossez (autodoc) aeffa9f270 api_docs
2025-03-13 16:07:03 +00:00

309 行
21 KiB
HTML
原始文件 永久链接 Blame 文件历史

此文件含有不可见的 Unicode 字符
此文件含有人类无法区分的不可见的 Unicode 字符，但可以由计算机进行不同的处理。 如果您是想特意这样的，可以安全地忽略该警告。 使用 Escape 按钮显示他们。
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
<meta name="generator" content="pdoc3 0.11.5">
<title>audiocraft.models.magnet API documentation</title>
<meta name="description" content="Main model for using MAGNeT. This will combine all the required components
and provide easy access to the generation API.">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => {
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
hljs.highlightAll();
/* Collapse source docstrings */
setTimeout(() => {
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
.forEach(el => {
let d = document.createElement('details');
d.classList.add('hljs-string');
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
el.replaceWith(d);
});
}, 100);
})</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>audiocraft.models.magnet</code></h1>
</header>
<section id="section-intro">
<p>Main model for using MAGNeT. This will combine all the required components
and provide easy access to the generation API.</p>
</section>
<section>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-classes">Classes</h2>
<dl>
<dt id="audiocraft.models.magnet.MAGNeT"><code class="flex name class">
<span>class <span class="ident">MAGNeT</span></span>
<span>(</span><span>**kwargs)</span>
</code></dt>
<dd>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class MAGNeT(BaseGenModel):
&#34;&#34;&#34;MAGNeT main model with convenient generation API.
Args:
See MusicGen class.
&#34;&#34;&#34;
def __init__(self, **kwargs):
super().__init__(**kwargs)
# MAGNeT operates over a fixed sequence length defined in it&#39;s config.
self.duration = self.lm.cfg.dataset.segment_duration
self.set_generation_params()
@staticmethod
def get_pretrained(name: str = &#39;facebook/magnet-small-10secs&#39;, device=None):
&#34;&#34;&#34;Return pretrained model, we provide six models:
- facebook/magnet-small-10secs (300M), text to music, 10-second audio samples.
# see: https://huggingface.co/facebook/magnet-small-10secs
- facebook/magnet-medium-10secs (1.5B), text to music, 10-second audio samples.
# see: https://huggingface.co/facebook/magnet-medium-10secs
- facebook/magnet-small-30secs (300M), text to music, 30-second audio samples.
# see: https://huggingface.co/facebook/magnet-small-30secs
- facebook/magnet-medium-30secs (1.5B), text to music, 30-second audio samples.
# see: https://huggingface.co/facebook/magnet-medium-30secs
- facebook/audio-magnet-small (300M), text to sound-effect (10-second samples).
# see: https://huggingface.co/facebook/audio-magnet-small
- facebook/audio-magnet-medium (1.5B), text to sound-effect (10-second samples).
# see: https://huggingface.co/facebook/audio-magnet-medium
&#34;&#34;&#34;
if device is None:
if torch.cuda.device_count():
device = &#39;cuda&#39;
else:
device = &#39;cpu&#39;
compression_model = load_compression_model(name, device=device)
lm = load_lm_model_magnet(name, compression_model_frame_rate=int(compression_model.frame_rate), device=device)
if &#39;self_wav&#39; in lm.condition_provider.conditioners:
lm.condition_provider.conditioners[&#39;self_wav&#39;].match_len_on_eval = True
kwargs = {&#39;name&#39;: name, &#39;compression_model&#39;: compression_model, &#39;lm&#39;: lm}
return MAGNeT(**kwargs)
def set_generation_params(self, use_sampling: bool = True, top_k: int = 0,
top_p: float = 0.9, temperature: float = 3.0,
max_cfg_coef: float = 10.0, min_cfg_coef: float = 1.0,
decoding_steps: tp.List[int] = [20, 10, 10, 10],
span_arrangement: str = &#39;nonoverlap&#39;):
&#34;&#34;&#34;Set the generation parameters for MAGNeT.
Args:
use_sampling (bool, optional): Use sampling if True, else do argmax decoding. Defaults to True.
top_k (int, optional): top_k used for sampling. Defaults to 0.
top_p (float, optional): top_p used for sampling, when set to 0 top_k is used. Defaults to 0.9.
temperature (float, optional): Initial softmax temperature parameter. Defaults to 3.0.
max_cfg_coef (float, optional): Coefficient used for classifier free guidance. Defaults to 10.0.
min_cfg_coef (float, optional): End coefficient of classifier free guidance annealing. Defaults to 1.0.
decoding_steps (list of n_q ints, optional): The number of iterative decoding steps,
for each of the n_q RVQ codebooks.
span_arrangement (str, optional): Use either non-overlapping spans (&#39;nonoverlap&#39;)
or overlapping spans (&#39;stride1&#39;) in the masking scheme.
&#34;&#34;&#34;
self.generation_params = {
&#39;use_sampling&#39;: use_sampling,
&#39;temp&#39;: temperature,
&#39;top_k&#39;: top_k,
&#39;top_p&#39;: top_p,
&#39;max_cfg_coef&#39;: max_cfg_coef,
&#39;min_cfg_coef&#39;: min_cfg_coef,
&#39;decoding_steps&#39;: [int(s) for s in decoding_steps],
&#39;span_arrangement&#39;: span_arrangement
}</code></pre>
</details>
<div class="desc"><p>MAGNeT main model with convenient generation API.</p>
<h2 id="args">Args</h2>
<p>See MusicGen class.</p></div>
<h3>Ancestors</h3>
<ul class="hlist">
<li><a title="audiocraft.models.genmodel.BaseGenModel" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel">BaseGenModel</a></li>
<li>abc.ABC</li>
</ul>
<h3>Static methods</h3>
<dl>
<dt id="audiocraft.models.magnet.MAGNeT.get_pretrained"><code class="name flex">
<span>def <span class="ident">get_pretrained</span></span>(<span>name: str = 'facebook/magnet-small-10secs', device=None)</span>
</code></dt>
<dd>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">@staticmethod
def get_pretrained(name: str = &#39;facebook/magnet-small-10secs&#39;, device=None):
&#34;&#34;&#34;Return pretrained model, we provide six models:
- facebook/magnet-small-10secs (300M), text to music, 10-second audio samples.
# see: https://huggingface.co/facebook/magnet-small-10secs
- facebook/magnet-medium-10secs (1.5B), text to music, 10-second audio samples.
# see: https://huggingface.co/facebook/magnet-medium-10secs
- facebook/magnet-small-30secs (300M), text to music, 30-second audio samples.
# see: https://huggingface.co/facebook/magnet-small-30secs
- facebook/magnet-medium-30secs (1.5B), text to music, 30-second audio samples.
# see: https://huggingface.co/facebook/magnet-medium-30secs
- facebook/audio-magnet-small (300M), text to sound-effect (10-second samples).
# see: https://huggingface.co/facebook/audio-magnet-small
- facebook/audio-magnet-medium (1.5B), text to sound-effect (10-second samples).
# see: https://huggingface.co/facebook/audio-magnet-medium
&#34;&#34;&#34;
if device is None:
if torch.cuda.device_count():
device = &#39;cuda&#39;
else:
device = &#39;cpu&#39;
compression_model = load_compression_model(name, device=device)
lm = load_lm_model_magnet(name, compression_model_frame_rate=int(compression_model.frame_rate), device=device)
if &#39;self_wav&#39; in lm.condition_provider.conditioners:
lm.condition_provider.conditioners[&#39;self_wav&#39;].match_len_on_eval = True
kwargs = {&#39;name&#39;: name, &#39;compression_model&#39;: compression_model, &#39;lm&#39;: lm}
return MAGNeT(**kwargs)</code></pre>
</details>
<div class="desc"><p>Return pretrained model, we provide six models:
- facebook/magnet-small-10secs (300M), text to music, 10-second audio samples.
# see: <a href="https://huggingface.co/facebook/magnet-small-10secs">https://huggingface.co/facebook/magnet-small-10secs</a>
- facebook/magnet-medium-10secs (1.5B), text to music, 10-second audio samples.
# see: <a href="https://huggingface.co/facebook/magnet-medium-10secs">https://huggingface.co/facebook/magnet-medium-10secs</a>
- facebook/magnet-small-30secs (300M), text to music, 30-second audio samples.
# see: <a href="https://huggingface.co/facebook/magnet-small-30secs">https://huggingface.co/facebook/magnet-small-30secs</a>
- facebook/magnet-medium-30secs (1.5B), text to music, 30-second audio samples.
# see: <a href="https://huggingface.co/facebook/magnet-medium-30secs">https://huggingface.co/facebook/magnet-medium-30secs</a>
- facebook/audio-magnet-small (300M), text to sound-effect (10-second samples).
# see: <a href="https://huggingface.co/facebook/audio-magnet-small">https://huggingface.co/facebook/audio-magnet-small</a>
- facebook/audio-magnet-medium (1.5B), text to sound-effect (10-second samples).
# see: <a href="https://huggingface.co/facebook/audio-magnet-medium">https://huggingface.co/facebook/audio-magnet-medium</a></p></div>
</dd>
</dl>
<h3>Methods</h3>
<dl>
<dt id="audiocraft.models.magnet.MAGNeT.set_generation_params"><code class="name flex">
<span>def <span class="ident">set_generation_params</span></span>(<span>self,<br>use_sampling: bool = True,<br>top_k: int = 0,<br>top_p: float = 0.9,<br>temperature: float = 3.0,<br>max_cfg_coef: float = 10.0,<br>min_cfg_coef: float = 1.0,<br>decoding_steps: List[int] = [20, 10, 10, 10],<br>span_arrangement: str = 'nonoverlap')</span>
</code></dt>
<dd>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def set_generation_params(self, use_sampling: bool = True, top_k: int = 0,
top_p: float = 0.9, temperature: float = 3.0,
max_cfg_coef: float = 10.0, min_cfg_coef: float = 1.0,
decoding_steps: tp.List[int] = [20, 10, 10, 10],
span_arrangement: str = &#39;nonoverlap&#39;):
&#34;&#34;&#34;Set the generation parameters for MAGNeT.
Args:
use_sampling (bool, optional): Use sampling if True, else do argmax decoding. Defaults to True.
top_k (int, optional): top_k used for sampling. Defaults to 0.
top_p (float, optional): top_p used for sampling, when set to 0 top_k is used. Defaults to 0.9.
temperature (float, optional): Initial softmax temperature parameter. Defaults to 3.0.
max_cfg_coef (float, optional): Coefficient used for classifier free guidance. Defaults to 10.0.
min_cfg_coef (float, optional): End coefficient of classifier free guidance annealing. Defaults to 1.0.
decoding_steps (list of n_q ints, optional): The number of iterative decoding steps,
for each of the n_q RVQ codebooks.
span_arrangement (str, optional): Use either non-overlapping spans (&#39;nonoverlap&#39;)
or overlapping spans (&#39;stride1&#39;) in the masking scheme.
&#34;&#34;&#34;
self.generation_params = {
&#39;use_sampling&#39;: use_sampling,
&#39;temp&#39;: temperature,
&#39;top_k&#39;: top_k,
&#39;top_p&#39;: top_p,
&#39;max_cfg_coef&#39;: max_cfg_coef,
&#39;min_cfg_coef&#39;: min_cfg_coef,
&#39;decoding_steps&#39;: [int(s) for s in decoding_steps],
&#39;span_arrangement&#39;: span_arrangement
}</code></pre>
</details>
<div class="desc"><p>Set the generation parameters for MAGNeT.</p>
<h2 id="args">Args</h2>
<dl>
<dt><strong><code>use_sampling</code></strong> :&ensp;<code>bool</code>, optional</dt>
<dd>Use sampling if True, else do argmax decoding. Defaults to True.</dd>
<dt><strong><code>top_k</code></strong> :&ensp;<code>int</code>, optional</dt>
<dd>top_k used for sampling. Defaults to 0.</dd>
<dt><strong><code>top_p</code></strong> :&ensp;<code>float</code>, optional</dt>
<dd>top_p used for sampling, when set to 0 top_k is used. Defaults to 0.9.</dd>
<dt><strong><code>temperature</code></strong> :&ensp;<code>float</code>, optional</dt>
<dd>Initial softmax temperature parameter. Defaults to 3.0.</dd>
<dt><strong><code>max_cfg_coef</code></strong> :&ensp;<code>float</code>, optional</dt>
<dd>Coefficient used for classifier free guidance. Defaults to 10.0.</dd>
<dt><strong><code>min_cfg_coef</code></strong> :&ensp;<code>float</code>, optional</dt>
<dd>End coefficient of classifier free guidance annealing. Defaults to 1.0.</dd>
<dt><strong><code>decoding_steps</code></strong> :&ensp;<code>list</code> of <code>n_q ints</code>, optional</dt>
<dd>The number of iterative decoding steps,
for each of the n_q RVQ codebooks.</dd>
<dt><strong><code>span_arrangement</code></strong> :&ensp;<code>str</code>, optional</dt>
<dd>Use either non-overlapping spans ('nonoverlap')
or overlapping spans ('stride1') in the masking scheme.</dd>
</dl></div>
</dd>
</dl>
<h3>Inherited members</h3>
<ul class="hlist">
<li><code><b><a title="audiocraft.models.genmodel.BaseGenModel" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel">BaseGenModel</a></b></code>:
<ul class="hlist">
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.audio_channels" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.audio_channels">audio_channels</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.frame_rate" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.frame_rate">frame_rate</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.generate" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.generate">generate</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.generate_audio" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.generate_audio">generate_audio</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.generate_continuation" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.generate_continuation">generate_continuation</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.generate_unconditional" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.generate_unconditional">generate_unconditional</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.sample_rate" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.sample_rate">sample_rate</a></code></li>
<li><code><a title="audiocraft.models.genmodel.BaseGenModel.set_custom_progress_callback" href="genmodel.html#audiocraft.models.genmodel.BaseGenModel.set_custom_progress_callback">set_custom_progress_callback</a></code></li>
</ul>
</li>
</ul>
</dd>
</dl>
</section>
</article>
<nav id="sidebar">
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3>Super-module</h3>
<ul>
<li><code><a title="audiocraft.models" href="index.html">audiocraft.models</a></code></li>
</ul>
</li>
<li><h3><a href="#header-classes">Classes</a></h3>
<ul>
<li>
<h4><code><a title="audiocraft.models.magnet.MAGNeT" href="#audiocraft.models.magnet.MAGNeT">MAGNeT</a></code></h4>
<ul class="">
<li><code><a title="audiocraft.models.magnet.MAGNeT.get_pretrained" href="#audiocraft.models.magnet.MAGNeT.get_pretrained">get_pretrained</a></code></li>
<li><code><a title="audiocraft.models.magnet.MAGNeT.set_generation_params" href="#audiocraft.models.magnet.MAGNeT.set_generation_params">set_generation_params</a></code></li>
</ul>
</li>
</ul>
</li>
</ul>
</nav>
</main>
<footer id="footer">
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
</footer>
</body>
</html>
在新工单中引用 查看 Git Blame 复制永久链接