facebookresearch--audiocraft
Alexandre Défossez (autodoc)
223 行
14 KiB
HTML
223 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.watermark 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.watermark</code></h1>
|
||
</header>
|
||
<section id="section-intro">
|
||
</section>
|
||
<section>
|
||
</section>
|
||
<section>
|
||
</section>
|
||
<section>
|
||
<h2 class="section-title" id="header-functions">Functions</h2>
|
||
<dl>
|
||
<dt id="audiocraft.modules.watermark.mix"><code class="name flex">
|
||
<span>def <span class="ident">mix</span></span>(<span>x: torch.Tensor,<br>x_wm: torch.Tensor,<br>window_size: float = 0.5,<br>shuffle: bool = False) ‑> Tuple[torch.Tensor, torch.Tensor]</span>
|
||
</code></dt>
|
||
<dd>
|
||
<details class="source">
|
||
<summary>
|
||
<span>Expand source code</span>
|
||
</summary>
|
||
<pre><code class="python">def mix(
|
||
x: torch.Tensor, x_wm: torch.Tensor, window_size: float = 0.5, shuffle: bool = False
|
||
) -> tp.Tuple[torch.Tensor, torch.Tensor]:
|
||
"""
|
||
Mixes a window of the non-watermarked audio signal 'x' into the watermarked audio signal 'x_wm'.
|
||
|
||
This function takes two tensors of shape [batch, channels, frames], copies a window of 'x' with the specified
|
||
'window_size' into 'x_wm', and returns a new tensor that is a mix between the watermarked (1 - mix_percent %)
|
||
and non-watermarked audio (mix_percent %).
|
||
|
||
Args:
|
||
x (torch.Tensor): The non-watermarked audio signal tensor.
|
||
x_wm (torch.Tensor): The watermarked audio signal tensor.
|
||
window_size (float, optional): The percentage of 'x' to copy into 'x_wm' (between 0 and 1).
|
||
shuffle (bool): whether or no keep the mix from the same batch element
|
||
|
||
Returns:
|
||
tuple: A tuple containing two tensors:
|
||
- mixed_tensor (torch.Tensor): The resulting mixed audio signal tensor.
|
||
- mask (torch.Tensor): A binary mask where 1 represents watermarked and 0 represents non-watermarked.
|
||
|
||
Raises:
|
||
AssertionError: If 'window_size' is not between 0 and 1.
|
||
"""
|
||
assert 0 < window_size <= 1, "window_size should be between 0 and 1"
|
||
|
||
# Calculate the maximum starting point for the window
|
||
max_start_point = x.shape[-1] - int(window_size * x.shape[-1])
|
||
|
||
# Generate a random starting point within the adjusted valid range
|
||
start_point = random.randint(0, max_start_point)
|
||
|
||
# Calculate the window size in frames
|
||
total_frames = x.shape[-1]
|
||
window_frames = int(window_size * total_frames)
|
||
|
||
# Create a mask tensor to identify watermarked and non-watermarked portions
|
||
# it outputs two classes to match the detector output shape of [bsz, 2, frames]
|
||
# Copy the random window from 'x' to 'x_wm'
|
||
mixed = x_wm.detach().clone()
|
||
|
||
true_predictions = torch.cat(
|
||
[torch.zeros_like(mixed), torch.ones_like(mixed)], dim=1
|
||
)
|
||
# non-watermark class correct labels.
|
||
true_predictions[:, 0, start_point: start_point + window_frames] = 1.0
|
||
# watermarked class correct labels
|
||
true_predictions[:, 1, start_point: start_point + window_frames] = 0.0
|
||
|
||
if shuffle:
|
||
# Take the middle part from a random element of the batch
|
||
shuffle_idx = torch.randint(0, x.size(0), (x.size(0),))
|
||
mixed[:, :, start_point: start_point + window_frames] = x[shuffle_idx][
|
||
:, :, start_point: start_point + window_frames
|
||
]
|
||
else:
|
||
mixed[:, :, start_point: start_point + window_frames] = x[
|
||
:, :, start_point: start_point + window_frames
|
||
]
|
||
|
||
return mixed, true_predictions</code></pre>
|
||
</details>
|
||
<div class="desc"><p>Mixes a window of the non-watermarked audio signal 'x' into the watermarked audio signal 'x_wm'.</p>
|
||
<p>This function takes two tensors of shape [batch, channels, frames], copies a window of 'x' with the specified
|
||
'window_size' into 'x_wm', and returns a new tensor that is a mix between the watermarked (1 - mix_percent %)
|
||
and non-watermarked audio (mix_percent %).</p>
|
||
<h2 id="args">Args</h2>
|
||
<dl>
|
||
<dt><strong><code>x</code></strong> : <code>torch.Tensor</code></dt>
|
||
<dd>The non-watermarked audio signal tensor.</dd>
|
||
<dt><strong><code>x_wm</code></strong> : <code>torch.Tensor</code></dt>
|
||
<dd>The watermarked audio signal tensor.</dd>
|
||
<dt><strong><code>window_size</code></strong> : <code>float</code>, optional</dt>
|
||
<dd>The percentage of 'x' to copy into 'x_wm' (between 0 and 1).</dd>
|
||
<dt><strong><code>shuffle</code></strong> : <code>bool</code></dt>
|
||
<dd>whether or no keep the mix from the same batch element</dd>
|
||
</dl>
|
||
<h2 id="returns">Returns</h2>
|
||
<dl>
|
||
<dt><code>tuple</code></dt>
|
||
<dd>A tuple containing two tensors:
|
||
- mixed_tensor (torch.Tensor): The resulting mixed audio signal tensor.
|
||
- mask (torch.Tensor): A binary mask where 1 represents watermarked and 0 represents non-watermarked.</dd>
|
||
</dl>
|
||
<h2 id="raises">Raises</h2>
|
||
<dl>
|
||
<dt><code>AssertionError</code></dt>
|
||
<dd>If 'window_size' is not between 0 and 1.</dd>
|
||
</dl></div>
|
||
</dd>
|
||
<dt id="audiocraft.modules.watermark.pad"><code class="name flex">
|
||
<span>def <span class="ident">pad</span></span>(<span>x_wm: torch.Tensor, central: bool = False) ‑> Tuple[torch.Tensor, torch.Tensor]</span>
|
||
</code></dt>
|
||
<dd>
|
||
<details class="source">
|
||
<summary>
|
||
<span>Expand source code</span>
|
||
</summary>
|
||
<pre><code class="python">def pad(
|
||
x_wm: torch.Tensor, central: bool = False
|
||
) -> tp.Tuple[torch.Tensor, torch.Tensor]:
|
||
"""Pad a watermarked signal at the begining and the end
|
||
|
||
Args:
|
||
x_wm (torch.Tensor) : watermarked audio
|
||
central (bool): Whether to mask the middle of the wave (around 34%) or the two tails
|
||
(beginning and ending frames)
|
||
|
||
Returns:
|
||
padded (torch.Tensor): padded signal
|
||
true_predictions(torch.Tensor): A binary mask where 1 represents
|
||
watermarked and 0 represents non-watermarked."""
|
||
# keep at leat 34% of watermarked signal
|
||
max_start = int(0.33 * x_wm.size(-1))
|
||
min_end = int(0.66 * x_wm.size(-1))
|
||
starts = torch.randint(0, max_start, size=(x_wm.size(0),))
|
||
ends = torch.randint(min_end, x_wm.size(-1), size=(x_wm.size(0),))
|
||
mask = torch.zeros_like(x_wm)
|
||
for i in range(x_wm.size(0)):
|
||
mask[i, :, starts[i]: ends[i]] = 1
|
||
if central:
|
||
mask = 1 - mask
|
||
padded = x_wm * mask
|
||
true_predictions = torch.cat([1 - mask, mask], dim=1)
|
||
return padded, true_predictions</code></pre>
|
||
</details>
|
||
<div class="desc"><p>Pad a watermarked signal at the begining and the end</p>
|
||
<h2 id="args">Args</h2>
|
||
<dl>
|
||
<dt>x_wm (torch.Tensor) : watermarked audio</dt>
|
||
<dt><strong><code>central</code></strong> : <code>bool</code></dt>
|
||
<dd>Whether to mask the middle of the wave (around 34%) or the two tails
|
||
(beginning and ending frames)</dd>
|
||
</dl>
|
||
<h2 id="returns">Returns</h2>
|
||
<p>padded (torch.Tensor): padded signal
|
||
true_predictions(torch.Tensor): A binary mask where 1 represents
|
||
watermarked and 0 represents non-watermarked.</p></div>
|
||
</dd>
|
||
</dl>
|
||
</section>
|
||
<section>
|
||
</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-functions">Functions</a></h3>
|
||
<ul class="">
|
||
<li><code><a title="audiocraft.modules.watermark.mix" href="#audiocraft.modules.watermark.mix">mix</a></code></li>
|
||
<li><code><a title="audiocraft.modules.watermark.pad" href="#audiocraft.modules.watermark.pad">pad</a></code></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>
|