diffusers/pr_14217/en/_app/immutable/nodes/30.nD0U6GLn.js

import"../chunks/DsnmJJEf.js";import{i as G,h as M,C as E,H as d,D as o,E as S,s as C}from"../chunks/BtE7mKSK.js";import{p as H,o as F,s as e,f as N,a as k,b as W,c as t,d as x,n,r}from"../chunks/jDjavuwI.js";const K='{"title":"AutoencoderOobleck","local":"autoencoderoobleck","sections":[{"title":"AutoencoderOobleck","local":"diffusers.AutoencoderOobleck","sections":[],"depth":2},{"title":"OobleckDecoderOutput","local":"diffusers.models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput","sections":[],"depth":2},{"title":"AutoencoderOobleckOutput","local":"diffusers.models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput","sections":[],"depth":2}],"depth":1}';var P=x('<meta name="hf:doc:metadata"/>'),q=x(`<p></p> <!> <!> <p>The Oobleck variational autoencoder (VAE) model with KL loss was introduced in <a href="https://github.com/Stability-AI/stable-audio-tools" rel="nofollow">Stability-AI/stable-audio-tools</a> and <a href="https://huggingface.co/papers/2407.14358" rel="nofollow">Stable Audio Open</a> by Stability AI. The model is used in 🤗 Diffusers to encode audio waveforms into latents and to decode latent representations into audio waveforms.</p> <p>The abstract from the paper is:</p> <p><em>Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model’s performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.</em></p> <!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>An autoencoder for encoding waveforms into latents and decoding latent representations into waveforms. First
introduced in Stable Audio.</p> <p>This model inherits from <a href="/docs/diffusers/pr_14217/en/api/models/overview#diffusers.ModelMixin">ModelMixin</a>. Check the superclass documentation for it’s generic methods implemented
for all models (such as downloading or saving).</p> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Decode a batch of images.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Encode a batch of images into latents.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!></div></div> <!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Output of decoding method.</p></div> <!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>Output of AutoencoderOobleck encoding method.</p></div> <!> <p></p>`,1);function j(A,w){H(w,!1),F(()=>{new URLSearchParams(window.location.search).get("fw")}),G();var u=q();M("uip9n0",v=>{var O=P();C(O,"content",K),k(v,O)});var p=e(N(u),2);E(p,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var m=e(p,2);d(m,{title:"AutoencoderOobleck",local:"autoencoderoobleck",headingTag:"h1"});var f=e(m,8);d(f,{title:"AutoencoderOobleck",local:"diffusers.AutoencoderOobleck",headingTag:"h2"});var a=e(f,2),h=t(a);o(h,{name:"class diffusers.AutoencoderOobleck",anchor:"diffusers.AutoencoderOobleck",source:"https://github.com/huggingface/diffusers/blob/vr_14217/src/diffusers/models/autoencoders/autoencoder_oobleck.py#L294",parameters:[{name:"encoder_hidden_size",val:" = 128"},{name:"downsampling_ratios",val:" = [2, 4, 4, 8, 8]"},{name:"channel_multiples",val:" = [1, 2, 4, 8, 16]"},{name:"decoder_channels",val:" = 128"},{name:"decoder_input_channels",val:" = 64"},{name:"audio_channels",val:" = 2"},{name:"sampling_rate",val:" = 44100"}],parametersDescription:[{anchor:"diffusers.AutoencoderOobleck.encoder_hidden_size",description:`<strong>encoder_hidden_size</strong> (<code>int</code>, <em>optional</em>, defaults to 128) &#x2014;
Intermediate representation dimension for the encoder.`,name:"encoder_hidden_size"},{anchor:"diffusers.AutoencoderOobleck.downsampling_ratios",description:`<strong>downsampling_ratios</strong> (<code>list[int]</code>, <em>optional</em>, defaults to <code>[2, 4, 4, 8, 8]</code>) &#x2014;
Ratios for downsampling in the encoder. These are used in reverse order for upsampling in the decoder.`,name:"downsampling_ratios"},{anchor:"diffusers.AutoencoderOobleck.channel_multiples",description:`<strong>channel_multiples</strong> (<code>list[int]</code>, <em>optional</em>, defaults to <code>[1, 2, 4, 8, 16]</code>) &#x2014;
Multiples used to determine the hidden sizes of the hidden layers.`,name:"channel_multiples"},{anchor:"diffusers.AutoencoderOobleck.decoder_channels",description:`<strong>decoder_channels</strong> (<code>int</code>, <em>optional</em>, defaults to 128) &#x2014;
Intermediate representation dimension for the decoder.`,name:"decoder_channels"},{anchor:"diffusers.AutoencoderOobleck.decoder_input_channels",description:`<strong>decoder_input_channels</strong> (<code>int</code>, <em>optional</em>, defaults to 64) &#x2014;
Input dimension for the decoder. Corresponds to the latent dimension.`,name:"decoder_input_channels"},{anchor:"diffusers.AutoencoderOobleck.audio_channels",description:`<strong>audio_channels</strong> (<code>int</code>, <em>optional</em>, defaults to 2) &#x2014;
Number of channels in the audio data. Either 1 for mono or 2 for stereo.`,name:"audio_channels"},{anchor:"diffusers.AutoencoderOobleck.sampling_rate",description:`<strong>sampling_rate</strong> (<code>int</code>, <em>optional</em>, defaults to 44100) &#x2014;
The sampling rate at which the audio waveform should be digitalized expressed in hertz (Hz).`,name:"sampling_rate"}]});var s=e(h,6),D=t(s);o(D,{name:"decode",anchor:"diffusers.AutoencoderOobleck.decode",source:"https://github.com/huggingface/diffusers/blob/vr_14217/src/diffusers/models/autoencoders/autoencoder_oobleck.py#L488",parameters:[{name:"z",val:": FloatTensor"},{name:"return_dict",val:": bool = True"},{name:"generator",val:" = None"}],parametersDescription:[{anchor:"diffusers.AutoencoderOobleck.decode.z",description:"<strong>z</strong> (<code>torch.Tensor</code>) &#x2014; Input batch of latent vectors.",name:"z"},{anchor:"diffusers.AutoencoderOobleck.decode.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to return a <code>~models.vae.OobleckDecoderOutput</code> instead of a plain tuple.`,name:"return_dict"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If return_dict is True, a <code>~models.vae.OobleckDecoderOutput</code> is returned, otherwise a plain <code>tuple</code>
is returned.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~models.vae.OobleckDecoderOutput</code> or <code>tuple</code></p>
`}),n(2),r(s);var c=e(s,2),T=t(c);o(T,{name:"encode",anchor:"diffusers.AutoencoderOobleck.encode",source:"https://github.com/huggingface/diffusers/blob/vr_14217/src/diffusers/models/autoencoders/autoencoder_oobleck.py#L377",parameters:[{name:"x",val:": Tensor"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.AutoencoderOobleck.encode.x",description:"<strong>x</strong> (<code>torch.Tensor</code>) &#x2014; Input batch of images.",name:"x"},{anchor:"diffusers.AutoencoderOobleck.encode.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to return a <code>~models.autoencoder_kl.AutoencoderKLOutput</code> instead of a plain tuple.`,name:"return_dict"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The latent representations of the encoded images. If <code>return_dict</code> is True, a
<code>~models.autoencoder_kl.AutoencoderKLOutput</code> is returned, otherwise a plain <code>tuple</code> is returned.</p>
`}),n(2),r(c);var b=e(c,2),y=t(b);o(y,{name:"forward",anchor:"diffusers.AutoencoderOobleck.forward",source:"https://github.com/huggingface/diffusers/blob/vr_14217/src/diffusers/models/autoencoders/autoencoder_oobleck.py#L517",parameters:[{name:"sample",val:": Tensor"},{name:"sample_posterior",val:": bool = False"},{name:"return_dict",val:": bool = True"},{name:"generator",val:": typing.Optional[torch.Generator] = None"}],parametersDescription:[{anchor:"diffusers.AutoencoderOobleck.forward.sample",description:"<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014; Input sample.",name:"sample"},{anchor:"diffusers.AutoencoderOobleck.forward.sample_posterior",description:`<strong>sample_posterior</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to sample from the posterior.`,name:"sample_posterior"},{anchor:"diffusers.AutoencoderOobleck.forward.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether or not to return a <code>OobleckDecoderOutput</code> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.AutoencoderOobleck.forward.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow"><code>torch.Generator</code></a> to make sampling
deterministic.`,name:"generator"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If <code>return_dict</code> is True, a <code>~models.vae.OobleckDecoderOutput</code> is returned, otherwise a plain <code>tuple</code>
is returned.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~models.vae.OobleckDecoderOutput</code> or <code>tuple</code></p>
`}),r(b),r(a);var g=e(a,2);d(g,{title:"OobleckDecoderOutput",local:"diffusers.models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput",headingTag:"h2"});var i=e(g,2),z=t(i);o(z,{name:"class diffusers.models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput",anchor:"diffusers.models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput",source:"https://github.com/huggingface/diffusers/blob/vr_14217/src/diffusers/models/autoencoders/autoencoder_oobleck.py#L202",parameters:[{name:"sample",val:": Tensor"}],parametersDescription:[{anchor:"diffusers.models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, audio_channels, sequence_length)</code>) &#x2014;
The decoded output sample from the last layer of the model.`,name:"sample"}]}),n(2),r(i);var _=e(i,2);d(_,{title:"AutoencoderOobleckOutput",local:"diffusers.models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput",headingTag:"h2"});var l=e(_,2),I=t(l);o(I,{name:"class diffusers.models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput",anchor:"diffusers.models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput",source:"https://github.com/huggingface/diffusers/blob/vr_14217/src/diffusers/models/autoencoders/autoencoder_oobleck.py#L187",parameters:[{name:"latent_dist",val:": OobleckDiagonalGaussianDistribution"}],parametersDescription:[{anchor:"diffusers.models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput.latent_dist",description:`<strong>latent_dist</strong> (<code>OobleckDiagonalGaussianDistribution</code>) &#x2014;
Encoded outputs of <code>Encoder</code> represented as the mean and standard deviation of
<code>OobleckDiagonalGaussianDistribution</code>. <code>OobleckDiagonalGaussianDistribution</code> allows for sampling latents
from the distribution.`,name:"latent_dist"}]}),n(2),r(l);var L=e(l,2);S(L,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/autoencoder_oobleck.md"}),n(2),k(A,u),W()}export{j as component};