facebookresearch--audiocraft
Alexandre Défossez (autodoc)
228 行
14 KiB
HTML
228 行
14 KiB
HTML
<!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.modules.chroma API documentation</title>
|
||
<meta name="description" content="">
|
||
<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.modules.chroma</code></h1>
|
||
</header>
|
||
<section id="section-intro">
|
||
</section>
|
||
<section>
|
||
</section>
|
||
<section>
|
||
</section>
|
||
<section>
|
||
</section>
|
||
<section>
|
||
<h2 class="section-title" id="header-classes">Classes</h2>
|
||
<dl>
|
||
<dt id="audiocraft.modules.chroma.ChromaExtractor"><code class="flex name class">
|
||
<span>class <span class="ident">ChromaExtractor</span></span>
|
||
<span>(</span><span>sample_rate: int,<br>n_chroma: int = 12,<br>radix2_exp: int = 12,<br>nfft: int | None = None,<br>winlen: int | None = None,<br>winhop: int | None = None,<br>argmax: bool = False,<br>norm: float = inf)</span>
|
||
</code></dt>
|
||
<dd>
|
||
<details class="source">
|
||
<summary>
|
||
<span>Expand source code</span>
|
||
</summary>
|
||
<pre><code class="python">class ChromaExtractor(nn.Module):
|
||
"""Chroma extraction and quantization.
|
||
|
||
Args:
|
||
sample_rate (int): Sample rate for the chroma extraction.
|
||
n_chroma (int): Number of chroma bins for the chroma extraction.
|
||
radix2_exp (int): Size of stft window for the chroma extraction (power of 2, e.g. 12 -> 2^12).
|
||
nfft (int, optional): Number of FFT.
|
||
winlen (int, optional): Window length.
|
||
winhop (int, optional): Window hop size.
|
||
argmax (bool, optional): Whether to use argmax. Defaults to False.
|
||
norm (float, optional): Norm for chroma normalization. Defaults to inf.
|
||
"""
|
||
def __init__(self, sample_rate: int, n_chroma: int = 12, radix2_exp: int = 12, nfft: tp.Optional[int] = None,
|
||
winlen: tp.Optional[int] = None, winhop: tp.Optional[int] = None, argmax: bool = False,
|
||
norm: float = torch.inf):
|
||
super().__init__()
|
||
self.winlen = winlen or 2 ** radix2_exp
|
||
self.nfft = nfft or self.winlen
|
||
self.winhop = winhop or (self.winlen // 4)
|
||
self.sample_rate = sample_rate
|
||
self.n_chroma = n_chroma
|
||
self.norm = norm
|
||
self.argmax = argmax
|
||
self.register_buffer('fbanks', torch.from_numpy(filters.chroma(sr=sample_rate, n_fft=self.nfft, tuning=0,
|
||
n_chroma=self.n_chroma)), persistent=False)
|
||
self.spec = torchaudio.transforms.Spectrogram(n_fft=self.nfft, win_length=self.winlen,
|
||
hop_length=self.winhop, power=2, center=True,
|
||
pad=0, normalized=True)
|
||
|
||
def forward(self, wav: torch.Tensor) -> torch.Tensor:
|
||
T = wav.shape[-1]
|
||
# in case we are getting a wav that was dropped out (nullified)
|
||
# from the conditioner, make sure wav length is no less that nfft
|
||
if T < self.nfft:
|
||
pad = self.nfft - T
|
||
r = 0 if pad % 2 == 0 else 1
|
||
wav = F.pad(wav, (pad // 2, pad // 2 + r), 'constant', 0)
|
||
assert wav.shape[-1] == self.nfft, f"expected len {self.nfft} but got {wav.shape[-1]}"
|
||
|
||
spec = self.spec(wav).squeeze(1)
|
||
raw_chroma = torch.einsum('cf,...ft->...ct', self.fbanks, spec)
|
||
norm_chroma = torch.nn.functional.normalize(raw_chroma, p=self.norm, dim=-2, eps=1e-6)
|
||
norm_chroma = rearrange(norm_chroma, 'b d t -> b t d')
|
||
|
||
if self.argmax:
|
||
idx = norm_chroma.argmax(-1, keepdim=True)
|
||
norm_chroma[:] = 0
|
||
norm_chroma.scatter_(dim=-1, index=idx, value=1)
|
||
|
||
return norm_chroma</code></pre>
|
||
</details>
|
||
<div class="desc"><p>Chroma extraction and quantization.</p>
|
||
<h2 id="args">Args</h2>
|
||
<dl>
|
||
<dt><strong><code>sample_rate</code></strong> : <code>int</code></dt>
|
||
<dd>Sample rate for the chroma extraction.</dd>
|
||
<dt><strong><code>n_chroma</code></strong> : <code>int</code></dt>
|
||
<dd>Number of chroma bins for the chroma extraction.</dd>
|
||
<dt><strong><code>radix2_exp</code></strong> : <code>int</code></dt>
|
||
<dd>Size of stft window for the chroma extraction (power of 2, e.g. 12 -> 2^12).</dd>
|
||
<dt><strong><code>nfft</code></strong> : <code>int</code>, optional</dt>
|
||
<dd>Number of FFT.</dd>
|
||
<dt><strong><code>winlen</code></strong> : <code>int</code>, optional</dt>
|
||
<dd>Window length.</dd>
|
||
<dt><strong><code>winhop</code></strong> : <code>int</code>, optional</dt>
|
||
<dd>Window hop size.</dd>
|
||
<dt><strong><code>argmax</code></strong> : <code>bool</code>, optional</dt>
|
||
<dd>Whether to use argmax. Defaults to False.</dd>
|
||
<dt><strong><code>norm</code></strong> : <code>float</code>, optional</dt>
|
||
<dd>Norm for chroma normalization. Defaults to inf.</dd>
|
||
</dl>
|
||
<p>Initializes internal Module state, shared by both nn.Module and ScriptModule.</p></div>
|
||
<h3>Ancestors</h3>
|
||
<ul class="hlist">
|
||
<li>torch.nn.modules.module.Module</li>
|
||
</ul>
|
||
<h3>Class variables</h3>
|
||
<dl>
|
||
<dt id="audiocraft.modules.chroma.ChromaExtractor.call_super_init"><code class="name">var <span class="ident">call_super_init</span> : bool</code></dt>
|
||
<dd>
|
||
<div class="desc"></div>
|
||
</dd>
|
||
<dt id="audiocraft.modules.chroma.ChromaExtractor.dump_patches"><code class="name">var <span class="ident">dump_patches</span> : bool</code></dt>
|
||
<dd>
|
||
<div class="desc"></div>
|
||
</dd>
|
||
<dt id="audiocraft.modules.chroma.ChromaExtractor.training"><code class="name">var <span class="ident">training</span> : bool</code></dt>
|
||
<dd>
|
||
<div class="desc"></div>
|
||
</dd>
|
||
</dl>
|
||
<h3>Methods</h3>
|
||
<dl>
|
||
<dt id="audiocraft.modules.chroma.ChromaExtractor.forward"><code class="name flex">
|
||
<span>def <span class="ident">forward</span></span>(<span>self, wav: torch.Tensor) ‑> torch.Tensor</span>
|
||
</code></dt>
|
||
<dd>
|
||
<details class="source">
|
||
<summary>
|
||
<span>Expand source code</span>
|
||
</summary>
|
||
<pre><code class="python">def forward(self, wav: torch.Tensor) -> torch.Tensor:
|
||
T = wav.shape[-1]
|
||
# in case we are getting a wav that was dropped out (nullified)
|
||
# from the conditioner, make sure wav length is no less that nfft
|
||
if T < self.nfft:
|
||
pad = self.nfft - T
|
||
r = 0 if pad % 2 == 0 else 1
|
||
wav = F.pad(wav, (pad // 2, pad // 2 + r), 'constant', 0)
|
||
assert wav.shape[-1] == self.nfft, f"expected len {self.nfft} but got {wav.shape[-1]}"
|
||
|
||
spec = self.spec(wav).squeeze(1)
|
||
raw_chroma = torch.einsum('cf,...ft->...ct', self.fbanks, spec)
|
||
norm_chroma = torch.nn.functional.normalize(raw_chroma, p=self.norm, dim=-2, eps=1e-6)
|
||
norm_chroma = rearrange(norm_chroma, 'b d t -> b t d')
|
||
|
||
if self.argmax:
|
||
idx = norm_chroma.argmax(-1, keepdim=True)
|
||
norm_chroma[:] = 0
|
||
norm_chroma.scatter_(dim=-1, index=idx, value=1)
|
||
|
||
return norm_chroma</code></pre>
|
||
</details>
|
||
<div class="desc"><p>Defines the computation performed at every call.</p>
|
||
<p>Should be overridden by all subclasses.</p>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>Although the recipe for forward pass needs to be defined within
|
||
this function, one should call the :class:<code>Module</code> instance afterwards
|
||
instead of this since the former takes care of running the
|
||
registered hooks while the latter silently ignores them.</p>
|
||
</div></div>
|
||
</dd>
|
||
</dl>
|
||
</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.modules" href="index.html">audiocraft.modules</a></code></li>
|
||
</ul>
|
||
</li>
|
||
<li><h3><a href="#header-classes">Classes</a></h3>
|
||
<ul>
|
||
<li>
|
||
<h4><code><a title="audiocraft.modules.chroma.ChromaExtractor" href="#audiocraft.modules.chroma.ChromaExtractor">ChromaExtractor</a></code></h4>
|
||
<ul class="">
|
||
<li><code><a title="audiocraft.modules.chroma.ChromaExtractor.call_super_init" href="#audiocraft.modules.chroma.ChromaExtractor.call_super_init">call_super_init</a></code></li>
|
||
<li><code><a title="audiocraft.modules.chroma.ChromaExtractor.dump_patches" href="#audiocraft.modules.chroma.ChromaExtractor.dump_patches">dump_patches</a></code></li>
|
||
<li><code><a title="audiocraft.modules.chroma.ChromaExtractor.forward" href="#audiocraft.modules.chroma.ChromaExtractor.forward">forward</a></code></li>
|
||
<li><code><a title="audiocraft.modules.chroma.ChromaExtractor.training" href="#audiocraft.modules.chroma.ChromaExtractor.training">training</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>
|