diffusers/main/en/_app/pages/api/pipelines/audio_diffusion.mdx-hf-doc-builder.js

import{S as wr,i as Mr,s as Dr,e as r,k as a,w as b,t as c,M as Pr,c as o,d as t,m as l,a as n,x as $,h as m,b as d,G as s,g,y as v,q as y,o as w,B as M,v as Ar,L as Bt}from"../../../chunks/vendor-hf-doc-builder.js";import{T as xr}from"../../../chunks/Tip-hf-doc-builder.js";import{D as I}from"../../../chunks/Docstring-hf-doc-builder.js";import{C as Ct}from"../../../chunks/CodeBlock-hf-doc-builder.js";import{I as is}from"../../../chunks/IconCopyLink-hf-doc-builder.js";import{E as Rt}from"../../../chunks/ExampleCodeBlock-hf-doc-builder.js";function Er(j){let f,A,h,p,D,i,_,U;return{c(){f=r("p"),A=c("Make sure to check out the Schedulers "),h=r("a"),p=c("guide"),D=c(" to learn how to explore the tradeoff between scheduler speed and quality, and see the "),i=r("a"),_=c("reuse components across pipelines"),U=c(" section to learn how to efficiently load the same components into multiple pipelines."),this.h()},l(L){f=o(L,"P",{});var J=n(f);A=m(J,"Make sure to check out the Schedulers "),h=o(J,"A",{href:!0});var N=n(h);p=m(N,"guide"),N.forEach(t),D=m(J," to learn how to explore the tradeoff between scheduler speed and quality, and see the "),i=o(J,"A",{href:!0});var G=n(i);_=m(G,"reuse components across pipelines"),G.forEach(t),U=m(J," section to learn how to efficiently load the same components into multiple pipelines."),J.forEach(t),this.h()},h(){d(h,"href","/using-diffusers/schedulers"),d(i,"href","/using-diffusers/loading#reuse-components-across-pipelines")},m(L,J){g(L,f,J),s(f,A),s(f,h),s(h,p),s(f,D),s(f,i),s(i,_),s(f,U)},d(L){L&&t(f)}}}function kr(j){let f,A,h,p,D;return p=new Ct({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> IPython.display <span class="hljs-keyword">import</span> Audio
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

device = <span class="hljs-string">&quot;cuda&quot;</span> <span class="hljs-keyword">if</span> torch.cuda.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">&quot;cpu&quot;</span>
pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;teticio/audio-diffusion-256&quot;</span>).to(device)

output = pipe()
display(output.images[<span class="hljs-number">0</span>])
display(Audio(output.audios[<span class="hljs-number">0</span>], rate=mel.get_sample_rate()))`}}),{c(){f=r("p"),A=c("For audio diffusion:"),h=a(),b(p.$$.fragment)},l(i){f=o(i,"P",{});var _=n(f);A=m(_,"For audio diffusion:"),_.forEach(t),h=l(i),$(p.$$.fragment,i)},m(i,_){g(i,f,_),s(f,A),g(i,h,_),v(p,i,_),D=!0},p:Bt,i(i){D||(y(p.$$.fragment,i),D=!0)},o(i){w(p.$$.fragment,i),D=!1},d(i){i&&t(f),i&&t(h),M(p,i)}}}function Ir(j){let f,A,h,p,D;return p=new Ct({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> IPython.display <span class="hljs-keyword">import</span> Audio
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

device = <span class="hljs-string">&quot;cuda&quot;</span> <span class="hljs-keyword">if</span> torch.cuda.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">&quot;cpu&quot;</span>
pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;teticio/latent-audio-diffusion-256&quot;</span>).to(device)

output = pipe()
display(output.images[<span class="hljs-number">0</span>])
display(Audio(output.audios[<span class="hljs-number">0</span>], rate=pipe.mel.get_sample_rate()))`}}),{c(){f=r("p"),A=c("For latent audio diffusion:"),h=a(),b(p.$$.fragment)},l(i){f=o(i,"P",{});var _=n(f);A=m(_,"For latent audio diffusion:"),_.forEach(t),h=l(i),$(p.$$.fragment,i)},m(i,_){g(i,f,_),s(f,A),g(i,h,_),v(p,i,_),D=!0},p:Bt,i(i){D||(y(p.$$.fragment,i),D=!0)},o(i){w(p.$$.fragment,i),D=!1},d(i){i&&t(f),i&&t(h),M(p,i)}}}function Tr(j){let f,A,h,p,D;return p=new Ct({props:{code:"b3V0cHV0JTIwJTNEJTIwcGlwZSglMEElMjAlMjAlMjAlMjByYXdfYXVkaW8lM0RvdXRwdXQuYXVkaW9zJTVCMCUyQyUyMDAlNUQlMkMlMEElMjAlMjAlMjAlMjBzdGFydF9zdGVwJTNEaW50KHBpcGUuZ2V0X2RlZmF1bHRfc3RlcHMoKSUyMCUyRiUyMDIpJTJDJTBBJTIwJTIwJTIwJTIwbWFza19zdGFydF9zZWNzJTNEMSUyQyUwQSUyMCUyMCUyMCUyMG1hc2tfZW5kX3NlY3MlM0QxJTJDJTBBKSUwQWRpc3BsYXkob3V0cHV0LmltYWdlcyU1QjAlNUQpJTBBZGlzcGxheShBdWRpbyhvdXRwdXQuYXVkaW9zJTVCMCU1RCUyQyUyMHJhdGUlM0RwaXBlLm1lbC5nZXRfc2FtcGxlX3JhdGUoKSkp",highlighted:`output = pipe(
    raw_audio=output.audios[<span class="hljs-number">0</span>, <span class="hljs-number">0</span>],
    start_step=<span class="hljs-built_in">int</span>(pipe.get_default_steps() / <span class="hljs-number">2</span>),
    mask_start_secs=<span class="hljs-number">1</span>,
    mask_end_secs=<span class="hljs-number">1</span>,
)
display(output.images[<span class="hljs-number">0</span>])
display(Audio(output.audios[<span class="hljs-number">0</span>], rate=pipe.mel.get_sample_rate()))`}}),{c(){f=r("p"),A=c("For other tasks like variation, inpainting, outpainting, etc:"),h=a(),b(p.$$.fragment)},l(i){f=o(i,"P",{});var _=n(f);A=m(_,"For other tasks like variation, inpainting, outpainting, etc:"),_.forEach(t),h=l(i),$(p.$$.fragment,i)},m(i,_){g(i,f,_),s(f,A),g(i,h,_),v(p,i,_),D=!0},p:Bt,i(i){D||(y(p.$$.fragment,i),D=!0)},o(i){w(p.$$.fragment,i),D=!1},d(i){i&&t(f),i&&t(h),M(p,i)}}}function Jr(j){let f,A,h,p,D,i,_,U,L,J,N,G,Ns,Gs,ns,C,Us,fe,Ls,Ws,as,F,ls,W,z,Se,pe,Vs,je,Zs,ds,x,ue,Xs,Ne,Rs,Bs,ce,Cs,Je,Fs,zs,Qs,E,me,Os,Ge,qs,Ys,Ue,Hs,Ks,Q,et,O,st,q,tt,Y,he,rt,Le,ot,it,H,ge,nt,We,at,lt,K,_e,dt,Ve,ft,fs,V,ee,Ze,be,pt,Xe,ut,ps,Z,$e,ct,Re,mt,us,X,se,Be,ve,ht,Ce,gt,cs,R,ye,_t,Fe,bt,ms,B,te,ze,we,$t,Qe,vt,hs,P,Me,yt,re,De,wt,Oe,Mt,Dt,oe,Pe,Pt,qe,At,xt,ie,Ae,Et,Ye,kt,It,ne,xe,Tt,He,Jt,St,ae,Ee,jt,Ke,Nt,Gt,le,ke,Ut,es,Lt,Wt,de,Ie,Vt,ss,Zt,gs;return i=new is({}),F=new xr({props:{$$slots:{default:[Er]},$$scope:{ctx:j}}}),pe=new is({}),ue=new I({props:{name:"class diffusers.AudioDiffusionPipeline",anchor:"diffusers.AudioDiffusionPipeline",parameters:[{name:"vqvae",val:": AutoencoderKL"},{name:"unet",val:": UNet2DConditionModel"},{name:"mel",val:": Mel"},{name:"scheduler",val:": typing.Union[diffusers.schedulers.scheduling_ddim.DDIMScheduler, diffusers.schedulers.scheduling_ddpm.DDPMScheduler]"}],parametersDescription:[{anchor:"diffusers.AudioDiffusionPipeline.vqae",description:`<strong>vqae</strong> (<a href="/docs/diffusers/main/en/api/models/autoencoderkl#diffusers.AutoencoderKL">AutoencoderKL</a>) &#x2014;
Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.`,name:"vqae"},{anchor:"diffusers.AudioDiffusionPipeline.unet",description:`<strong>unet</strong> (<a href="/docs/diffusers/main/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>) &#x2014;
A <code>UNet2DConditionModel</code> to denoise the encoded image latents.`,name:"unet"},{anchor:"diffusers.AudioDiffusionPipeline.mel",description:`<strong>mel</strong> (<a href="/docs/diffusers/main/en/api/pipelines/audio_diffusion#diffusers.Mel">Mel</a>) &#x2014;
Transform audio into a spectrogram.`,name:"mel"},{anchor:"diffusers.AudioDiffusionPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/main/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a> or <a href="/docs/diffusers/main/en/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a>) &#x2014;
A scheduler to be used in combination with <code>unet</code> to denoise the encoded image latents. Can be one of
<a href="/docs/diffusers/main/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a> or <a href="/docs/diffusers/main/en/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a>.`,name:"scheduler"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py#L30"}}),me=new I({props:{name:"__call__",anchor:"diffusers.AudioDiffusionPipeline.__call__",parameters:[{name:"batch_size",val:": int = 1"},{name:"audio_file",val:": str = None"},{name:"raw_audio",val:": ndarray = None"},{name:"slice",val:": int = 0"},{name:"start_step",val:": int = 0"},{name:"steps",val:": int = None"},{name:"generator",val:": Generator = None"},{name:"mask_start_secs",val:": float = 0"},{name:"mask_end_secs",val:": float = 0"},{name:"step_generator",val:": Generator = None"},{name:"eta",val:": float = 0"},{name:"noise",val:": Tensor = None"},{name:"encoding",val:": Tensor = None"},{name:"return_dict",val:" = True"}],parametersDescription:[{anchor:"diffusers.AudioDiffusionPipeline.__call__.batch_size",description:`<strong>batch_size</strong> (<code>int</code>) &#x2014;
Number of samples to generate.`,name:"batch_size"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.audio_file",description:`<strong>audio_file</strong> (<code>str</code>) &#x2014;
An audio file that must be on disk due to <a href="https://librosa.org/" rel="nofollow">Librosa</a> limitation.`,name:"audio_file"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.raw_audio",description:`<strong>raw_audio</strong> (<code>np.ndarray</code>) &#x2014;
The raw audio file as a NumPy array.`,name:"raw_audio"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.slice",description:`<strong>slice</strong> (<code>int</code>) &#x2014;
Slice number of audio to convert.`,name:"slice"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.start_step",description:`<strong>start_step</strong> (int) &#x2014;
Step to start diffusion from.`,name:"start_step"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.steps",description:`<strong>steps</strong> (<code>int</code>) &#x2014;
Number of denoising steps (defaults to <code>50</code> for DDIM and <code>1000</code> for DDPM).`,name:"steps"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>) &#x2014;
A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow"><code>torch.Generator</code></a> to make
generation deterministic.`,name:"generator"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.mask_start_secs",description:`<strong>mask_start_secs</strong> (<code>float</code>) &#x2014;
Number of seconds of audio to mask (not generate) at start.`,name:"mask_start_secs"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.mask_end_secs",description:`<strong>mask_end_secs</strong> (<code>float</code>) &#x2014;
Number of seconds of audio to mask (not generate) at end.`,name:"mask_end_secs"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.step_generator",description:`<strong>step_generator</strong> (<code>torch.Generator</code>) &#x2014;
A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow"><code>torch.Generator</code></a> used to denoise.
None`,name:"step_generator"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.eta",description:`<strong>eta</strong> (<code>float</code>) &#x2014;
Corresponds to parameter eta (&#x3B7;) from the <a href="https://arxiv.org/abs/2010.02502" rel="nofollow">DDIM</a> paper. Only applies
to the <a href="/docs/diffusers/main/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a>, and is ignored in other schedulers.`,name:"eta"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.noise",description:`<strong>noise</strong> (<code>torch.Tensor</code>) &#x2014;
A noise tensor of shape <code>(batch_size, 1, height, width)</code> or <code>None</code>.`,name:"noise"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.encoding",description:`<strong>encoding</strong> (<code>torch.Tensor</code>) &#x2014;
A tensor for <a href="/docs/diffusers/main/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a> of shape <code>(batch_size, seq_length, cross_attention_dim)</code>.`,name:"encoding"},{anchor:"diffusers.AudioDiffusionPipeline.__call__.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>) &#x2014;
Whether or not to return a <a href="/docs/diffusers/main/en/api/pipelines/spectrogram_diffusion#diffusers.AudioPipelineOutput">AudioPipelineOutput</a>, <a href="/docs/diffusers/main/en/api/pipelines/vq_diffusion#diffusers.ImagePipelineOutput">ImagePipelineOutput</a> or a plain tuple.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py#L70",returnDescription:`
<p>A list of Mel spectrograms (<code>float</code>, <code>List[np.ndarray]</code>) with the sample rate and raw audio.</p>
`,returnType:`
<p><code>List[PIL Image]</code></p>
`}}),Q=new Rt({props:{anchor:"diffusers.AudioDiffusionPipeline.__call__.example",$$slots:{default:[kr]},$$scope:{ctx:j}}}),O=new Rt({props:{anchor:"diffusers.AudioDiffusionPipeline.__call__.example-2",$$slots:{default:[Ir]},$$scope:{ctx:j}}}),q=new Rt({props:{anchor:"diffusers.AudioDiffusionPipeline.__call__.example-3",$$slots:{default:[Tr]},$$scope:{ctx:j}}}),he=new I({props:{name:"encode",anchor:"diffusers.AudioDiffusionPipeline.encode",parameters:[{name:"images",val:": typing.List[PIL.Image.Image]"},{name:"steps",val:": int = 50"}],parametersDescription:[{anchor:"diffusers.AudioDiffusionPipeline.encode.images",description:`<strong>images</strong> (<code>List[PIL Image]</code>) &#x2014;
List of images to encode.`,name:"images"},{anchor:"diffusers.AudioDiffusionPipeline.encode.steps",description:`<strong>steps</strong> (<code>int</code>) &#x2014;
Number of encoding steps to perform (defaults to <code>50</code>).`,name:"steps"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py#L270",returnDescription:`
<p>A noise tensor of shape <code>(batch_size, 1, height, width)</code>.</p>
`,returnType:`
<p><code>np.ndarray</code></p>
`}}),ge=new I({props:{name:"get_default_steps",anchor:"diffusers.AudioDiffusionPipeline.get_default_steps",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py#L61",returnDescription:`
<p>The number of steps.</p>
`,returnType:`
<p><code>int</code></p>
`}}),_e=new I({props:{name:"slerp",anchor:"diffusers.AudioDiffusionPipeline.slerp",parameters:[{name:"x0",val:": Tensor"},{name:"x1",val:": Tensor"},{name:"alpha",val:": float"}],parametersDescription:[{anchor:"diffusers.AudioDiffusionPipeline.slerp.x0",description:`<strong>x0</strong> (<code>torch.Tensor</code>) &#x2014;
The first tensor to interpolate between.`,name:"x0"},{anchor:"diffusers.AudioDiffusionPipeline.slerp.x1",description:`<strong>x1</strong> (<code>torch.Tensor</code>) &#x2014;
Second tensor to interpolate between.`,name:"x1"},{anchor:"diffusers.AudioDiffusionPipeline.slerp.alpha",description:`<strong>alpha</strong> (<code>float</code>) &#x2014;
Interpolation between 0 and 1`,name:"alpha"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py#L311",returnDescription:`
<p>The interpolated tensor.</p>
`,returnType:`
<p><code>torch.Tensor</code></p>
`}}),be=new is({}),$e=new I({props:{name:"class diffusers.AudioPipelineOutput",anchor:"diffusers.AudioPipelineOutput",parameters:[{name:"audios",val:": ndarray"}],parametersDescription:[{anchor:"diffusers.AudioPipelineOutput.audios",description:`<strong>audios</strong> (<code>np.ndarray</code>) &#x2014;
List of denoised audio samples of a NumPy array of shape <code>(batch_size, num_channels, sample_rate)</code>.`,name:"audios"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L126"}}),ve=new is({}),ye=new I({props:{name:"class diffusers.ImagePipelineOutput",anchor:"diffusers.ImagePipelineOutput",parameters:[{name:"images",val:": typing.Union[typing.List[PIL.Image.Image], numpy.ndarray]"}],parametersDescription:[{anchor:"diffusers.ImagePipelineOutput.images",description:`<strong>images</strong> (<code>List[PIL.Image.Image]</code> or <code>np.ndarray</code>) &#x2014;
List of denoised PIL images of length <code>batch_size</code> or NumPy array of shape <code>(batch_size, height, width, num_channels)</code>.`,name:"images"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L112"}}),we=new is({}),Me=new I({props:{name:"class diffusers.Mel",anchor:"diffusers.Mel",parameters:[{name:"x_res",val:": int = 256"},{name:"y_res",val:": int = 256"},{name:"sample_rate",val:": int = 22050"},{name:"n_fft",val:": int = 2048"},{name:"hop_length",val:": int = 512"},{name:"top_db",val:": int = 80"},{name:"n_iter",val:": int = 32"}],parametersDescription:[{anchor:"diffusers.Mel.x_res",description:`<strong>x_res</strong> (<code>int</code>) &#x2014;
x resolution of spectrogram (time).`,name:"x_res"},{anchor:"diffusers.Mel.y_res",description:`<strong>y_res</strong> (<code>int</code>) &#x2014;
y resolution of spectrogram (frequency bins).`,name:"y_res"},{anchor:"diffusers.Mel.sample_rate",description:`<strong>sample_rate</strong> (<code>int</code>) &#x2014;
Sample rate of audio.`,name:"sample_rate"},{anchor:"diffusers.Mel.n_fft",description:`<strong>n_fft</strong> (<code>int</code>) &#x2014;
Number of Fast Fourier Transforms.`,name:"n_fft"},{anchor:"diffusers.Mel.hop_length",description:`<strong>hop_length</strong> (<code>int</code>) &#x2014;
Hop length (a higher number is recommended if <code>y_res</code> &lt; 256).`,name:"hop_length"},{anchor:"diffusers.Mel.top_db",description:`<strong>top_db</strong> (<code>int</code>) &#x2014;
Loudest decibel value.`,name:"top_db"},{anchor:"diffusers.Mel.n_iter",description:`<strong>n_iter</strong> (<code>int</code>) &#x2014;
Number of iterations for Griffin-Lim Mel inversion.`,name:"n_iter"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L37"}}),De=new I({props:{name:"audio_slice_to_image",anchor:"diffusers.Mel.audio_slice_to_image",parameters:[{name:"slice",val:": int"}],parametersDescription:[{anchor:"diffusers.Mel.audio_slice_to_image.slice",description:`<strong>slice</strong> (<code>int</code>) &#x2014;
Slice number of audio to convert (out of <code>get_number_of_slices()</code>).`,name:"slice"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L143",returnDescription:`
<p>A grayscale image of <code>x_res x y_res</code>.</p>
`,returnType:`
<p><code>PIL Image</code></p>
`}}),Pe=new I({props:{name:"get_audio_slice",anchor:"diffusers.Mel.get_audio_slice",parameters:[{name:"slice",val:": int = 0"}],parametersDescription:[{anchor:"diffusers.Mel.get_audio_slice.slice",description:`<strong>slice</strong> (<code>int</code>) &#x2014;
Slice number of audio (out of <code>get_number_of_slices()</code>).`,name:"slice"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L121",returnDescription:`
<p>The audio slice as a NumPy array.</p>
`,returnType:`
<p><code>np.ndarray</code></p>
`}}),Ae=new I({props:{name:"get_number_of_slices",anchor:"diffusers.Mel.get_number_of_slices",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L112",returnDescription:`
<p>Number of spectograms audio can be sliced into.</p>
`,returnType:`
<p><code>int</code></p>
`}}),xe=new I({props:{name:"get_sample_rate",anchor:"diffusers.Mel.get_sample_rate",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L134",returnDescription:`
<p>Sample rate of audio.</p>
`,returnType:`
<p><code>int</code></p>
`}}),Ee=new I({props:{name:"image_to_audio",anchor:"diffusers.Mel.image_to_audio",parameters:[{name:"image",val:": Image"}],parametersDescription:[{anchor:"diffusers.Mel.image_to_audio.image",description:`<strong>image</strong> (<code>PIL Image</code>) &#x2014;
An grayscale image of <code>x_res x y_res</code>.`,name:"image"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L162",returnDescription:`
<p>The audio as a NumPy array.</p>
`,returnType:`
<p>audio (<code>np.ndarray</code>)</p>
`}}),ke=new I({props:{name:"load_audio",anchor:"diffusers.Mel.load_audio",parameters:[{name:"audio_file",val:": str = None"},{name:"raw_audio",val:": ndarray = None"}],parametersDescription:[{anchor:"diffusers.Mel.load_audio.audio_file",description:`<strong>audio_file</strong> (<code>str</code>) &#x2014;
An audio file that must be on disk due to <a href="https://librosa.org/" rel="nofollow">Librosa</a> limitation.`,name:"audio_file"},{anchor:"diffusers.Mel.load_audio.raw_audio",description:`<strong>raw_audio</strong> (<code>np.ndarray</code>) &#x2014;
The raw audio file as a NumPy array.`,name:"raw_audio"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L94"}}),Ie=new I({props:{name:"set_resolution",anchor:"diffusers.Mel.set_resolution",parameters:[{name:"x_res",val:": int"},{name:"y_res",val:": int"}],parametersDescription:[{anchor:"diffusers.Mel.set_resolution.x_res",description:`<strong>x_res</strong> (<code>int</code>) &#x2014;
x resolution of spectrogram (time).`,name:"x_res"},{anchor:"diffusers.Mel.set_resolution.y_res",description:`<strong>y_res</strong> (<code>int</code>) &#x2014;
y resolution of spectrogram (frequency bins).`,name:"y_res"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/audio_diffusion/mel.py#L80"}}),{c(){f=r("meta"),A=a(),h=r("h1"),p=r("a"),D=r("span"),b(i.$$.fragment),_=a(),U=r("span"),L=c("Audio Diffusion"),J=a(),N=r("p"),G=r("a"),Ns=c("Audio Diffusion"),Gs=c(" is by Robert Dargavel Smith, and it leverages the recent advances in image generation from diffusion models by converting audio samples to and from Mel spectrogram images."),ns=a(),C=r("p"),Us=c("The original codebase, training scripts and example notebooks can be found at "),fe=r("a"),Ls=c("teticio/audio-diffusion"),Ws=c("."),as=a(),b(F.$$.fragment),ls=a(),W=r("h2"),z=r("a"),Se=r("span"),b(pe.$$.fragment),Vs=a(),je=r("span"),Zs=c("AudioDiffusionPipeline"),ds=a(),x=r("div"),b(ue.$$.fragment),Xs=a(),Ne=r("p"),Rs=c("Pipeline for audio diffusion."),Bs=a(),ce=r("p"),Cs=c("This model inherits from "),Je=r("a"),Fs=c("DiffusionPipeline"),zs=c(`. Check the superclass documentation for the generic methods
implemented for all pipelines (downloading, saving, running on a particular device, etc.).`),Qs=a(),E=r("div"),b(me.$$.fragment),Os=a(),Ge=r("p"),qs=c("The call function to the pipeline for generation."),Ys=a(),Ue=r("p"),Hs=c("Examples:"),Ks=a(),b(Q.$$.fragment),et=a(),b(O.$$.fragment),st=a(),b(q.$$.fragment),tt=a(),Y=r("div"),b(he.$$.fragment),rt=a(),Le=r("p"),ot=c("Reverse the denoising step process to recover a noisy image from the generated image."),it=a(),H=r("div"),b(ge.$$.fragment),nt=a(),We=r("p"),at=c("Returns default number of steps recommended for inference."),lt=a(),K=r("div"),b(_e.$$.fragment),dt=a(),Ve=r("p"),ft=c("Spherical Linear intERPolation."),fs=a(),V=r("h2"),ee=r("a"),Ze=r("span"),b(be.$$.fragment),pt=a(),Xe=r("span"),ut=c("AudioPipelineOutput"),ps=a(),Z=r("div"),b($e.$$.fragment),ct=a(),Re=r("p"),mt=c("Output class for audio pipelines."),us=a(),X=r("h2"),se=r("a"),Be=r("span"),b(ve.$$.fragment),ht=a(),Ce=r("span"),gt=c("ImagePipelineOutput"),cs=a(),R=r("div"),b(ye.$$.fragment),_t=a(),Fe=r("p"),bt=c("Output class for image pipelines."),ms=a(),B=r("h2"),te=r("a"),ze=r("span"),b(we.$$.fragment),$t=a(),Qe=r("span"),vt=c("Mel"),hs=a(),P=r("div"),b(Me.$$.fragment),yt=a(),re=r("div"),b(De.$$.fragment),wt=a(),Oe=r("p"),Mt=c("Convert slice of audio to spectrogram."),Dt=a(),oe=r("div"),b(Pe.$$.fragment),Pt=a(),qe=r("p"),At=c("Get slice of audio."),xt=a(),ie=r("div"),b(Ae.$$.fragment),Et=a(),Ye=r("p"),kt=c("Get number of slices in audio."),It=a(),ne=r("div"),b(xe.$$.fragment),Tt=a(),He=r("p"),Jt=c("Get sample rate."),St=a(),ae=r("div"),b(Ee.$$.fragment),jt=a(),Ke=r("p"),Nt=c("Converts spectrogram to audio."),Gt=a(),le=r("div"),b(ke.$$.fragment),Ut=a(),es=r("p"),Lt=c("Load audio."),Wt=a(),de=r("div"),b(Ie.$$.fragment),Vt=a(),ss=r("p"),Zt=c("Set resolution."),this.h()},l(e){const u=Pr('[data-svelte="svelte-1phssyn"]',document.head);f=o(u,"META",{name:!0,content:!0}),u.forEach(t),A=l(e),h=o(e,"H1",{class:!0});var Te=n(h);p=o(Te,"A",{id:!0,class:!0,href:!0});var ts=n(p);D=o(ts,"SPAN",{});var rs=n(D);$(i.$$.fragment,rs),rs.forEach(t),ts.forEach(t),_=l(Te),U=o(Te,"SPAN",{});var os=n(U);L=m(os,"Audio Diffusion"),os.forEach(t),Te.forEach(t),J=l(e),N=o(e,"P",{});var Xt=n(N);G=o(Xt,"A",{href:!0,rel:!0});var Ft=n(G);Ns=m(Ft,"Audio Diffusion"),Ft.forEach(t),Gs=m(Xt," is by Robert Dargavel Smith, and it leverages the recent advances in image generation from diffusion models by converting audio samples to and from Mel spectrogram images."),Xt.forEach(t),ns=l(e),C=o(e,"P",{});var _s=n(C);Us=m(_s,"The original codebase, training scripts and example notebooks can be found at "),fe=o(_s,"A",{href:!0,rel:!0});var zt=n(fe);Ls=m(zt,"teticio/audio-diffusion"),zt.forEach(t),Ws=m(_s,"."),_s.forEach(t),as=l(e),$(F.$$.fragment,e),ls=l(e),W=o(e,"H2",{class:!0});var bs=n(W);z=o(bs,"A",{id:!0,class:!0,href:!0});var Qt=n(z);Se=o(Qt,"SPAN",{});var Ot=n(Se);$(pe.$$.fragment,Ot),Ot.forEach(t),Qt.forEach(t),Vs=l(bs),je=o(bs,"SPAN",{});var qt=n(je);Zs=m(qt,"AudioDiffusionPipeline"),qt.forEach(t),bs.forEach(t),ds=l(e),x=o(e,"DIV",{class:!0});var T=n(x);$(ue.$$.fragment,T),Xs=l(T),Ne=o(T,"P",{});var Yt=n(Ne);Rs=m(Yt,"Pipeline for audio diffusion."),Yt.forEach(t),Bs=l(T),ce=o(T,"P",{});var $s=n(ce);Cs=m($s,"This model inherits from "),Je=o($s,"A",{href:!0});var Ht=n(Je);Fs=m(Ht,"DiffusionPipeline"),Ht.forEach(t),zs=m($s,`. Check the superclass documentation for the generic methods
implemented for all pipelines (downloading, saving, running on a particular device, etc.).`),$s.forEach(t),Qs=l(T),E=o(T,"DIV",{class:!0});var S=n(E);$(me.$$.fragment,S),Os=l(S),Ge=o(S,"P",{});var Kt=n(Ge);qs=m(Kt,"The call function to the pipeline for generation."),Kt.forEach(t),Ys=l(S),Ue=o(S,"P",{});var er=n(Ue);Hs=m(er,"Examples:"),er.forEach(t),Ks=l(S),$(Q.$$.fragment,S),et=l(S),$(O.$$.fragment,S),st=l(S),$(q.$$.fragment,S),S.forEach(t),tt=l(T),Y=o(T,"DIV",{class:!0});var vs=n(Y);$(he.$$.fragment,vs),rt=l(vs),Le=o(vs,"P",{});var sr=n(Le);ot=m(sr,"Reverse the denoising step process to recover a noisy image from the generated image."),sr.forEach(t),vs.forEach(t),it=l(T),H=o(T,"DIV",{class:!0});var ys=n(H);$(ge.$$.fragment,ys),nt=l(ys),We=o(ys,"P",{});var tr=n(We);at=m(tr,"Returns default number of steps recommended for inference."),tr.forEach(t),ys.forEach(t),lt=l(T),K=o(T,"DIV",{class:!0});var ws=n(K);$(_e.$$.fragment,ws),dt=l(ws),Ve=o(ws,"P",{});var rr=n(Ve);ft=m(rr,"Spherical Linear intERPolation."),rr.forEach(t),ws.forEach(t),T.forEach(t),fs=l(e),V=o(e,"H2",{class:!0});var Ms=n(V);ee=o(Ms,"A",{id:!0,class:!0,href:!0});var or=n(ee);Ze=o(or,"SPAN",{});var ir=n(Ze);$(be.$$.fragment,ir),ir.forEach(t),or.forEach(t),pt=l(Ms),Xe=o(Ms,"SPAN",{});var nr=n(Xe);ut=m(nr,"AudioPipelineOutput"),nr.forEach(t),Ms.forEach(t),ps=l(e),Z=o(e,"DIV",{class:!0});var Ds=n(Z);$($e.$$.fragment,Ds),ct=l(Ds),Re=o(Ds,"P",{});var ar=n(Re);mt=m(ar,"Output class for audio pipelines."),ar.forEach(t),Ds.forEach(t),us=l(e),X=o(e,"H2",{class:!0});var Ps=n(X);se=o(Ps,"A",{id:!0,class:!0,href:!0});var lr=n(se);Be=o(lr,"SPAN",{});var dr=n(Be);$(ve.$$.fragment,dr),dr.forEach(t),lr.forEach(t),ht=l(Ps),Ce=o(Ps,"SPAN",{});var fr=n(Ce);gt=m(fr,"ImagePipelineOutput"),fr.forEach(t),Ps.forEach(t),cs=l(e),R=o(e,"DIV",{class:!0});var As=n(R);$(ye.$$.fragment,As),_t=l(As),Fe=o(As,"P",{});var pr=n(Fe);bt=m(pr,"Output class for image pipelines."),pr.forEach(t),As.forEach(t),ms=l(e),B=o(e,"H2",{class:!0});var xs=n(B);te=o(xs,"A",{id:!0,class:!0,href:!0});var ur=n(te);ze=o(ur,"SPAN",{});var cr=n(ze);$(we.$$.fragment,cr),cr.forEach(t),ur.forEach(t),$t=l(xs),Qe=o(xs,"SPAN",{});var mr=n(Qe);vt=m(mr,"Mel"),mr.forEach(t),xs.forEach(t),hs=l(e),P=o(e,"DIV",{class:!0});var k=n(P);$(Me.$$.fragment,k),yt=l(k),re=o(k,"DIV",{class:!0});var Es=n(re);$(De.$$.fragment,Es),wt=l(Es),Oe=o(Es,"P",{});var hr=n(Oe);Mt=m(hr,"Convert slice of audio to spectrogram."),hr.forEach(t),Es.forEach(t),Dt=l(k),oe=o(k,"DIV",{class:!0});var ks=n(oe);$(Pe.$$.fragment,ks),Pt=l(ks),qe=o(ks,"P",{});var gr=n(qe);At=m(gr,"Get slice of audio."),gr.forEach(t),ks.forEach(t),xt=l(k),ie=o(k,"DIV",{class:!0});var Is=n(ie);$(Ae.$$.fragment,Is),Et=l(Is),Ye=o(Is,"P",{});var _r=n(Ye);kt=m(_r,"Get number of slices in audio."),_r.forEach(t),Is.forEach(t),It=l(k),ne=o(k,"DIV",{class:!0});var Ts=n(ne);$(xe.$$.fragment,Ts),Tt=l(Ts),He=o(Ts,"P",{});var br=n(He);Jt=m(br,"Get sample rate."),br.forEach(t),Ts.forEach(t),St=l(k),ae=o(k,"DIV",{class:!0});var Js=n(ae);$(Ee.$$.fragment,Js),jt=l(Js),Ke=o(Js,"P",{});var $r=n(Ke);Nt=m($r,"Converts spectrogram to audio."),$r.forEach(t),Js.forEach(t),Gt=l(k),le=o(k,"DIV",{class:!0});var Ss=n(le);$(ke.$$.fragment,Ss),Ut=l(Ss),es=o(Ss,"P",{});var vr=n(es);Lt=m(vr,"Load audio."),vr.forEach(t),Ss.forEach(t),Wt=l(k),de=o(k,"DIV",{class:!0});var js=n(de);$(Ie.$$.fragment,js),Vt=l(js),ss=o(js,"P",{});var yr=n(ss);Zt=m(yr,"Set resolution."),yr.forEach(t),js.forEach(t),k.forEach(t),this.h()},h(){d(f,"name","hf:doc:metadata"),d(f,"content",JSON.stringify(Sr)),d(p,"id","audio-diffusion"),d(p,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),d(p,"href","#audio-diffusion"),d(h,"class","relative group"),d(G,"href","https://github.com/teticio/audio-diffusion"),d(G,"rel","nofollow"),d(fe,"href","https://github.com/teticio/audio-diffusion"),d(fe,"rel","nofollow"),d(z,"id","diffusers.AudioDiffusionPipeline"),d(z,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),d(z,"href","#diffusers.AudioDiffusionPipeline"),d(W,"class","relative group"),d(Je,"href","/docs/diffusers/main/en/api/pipelines/overview#diffusers.DiffusionPipeline"),d(E,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(Y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(K,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(ee,"id","diffusers.AudioPipelineOutput"),d(ee,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),d(ee,"href","#diffusers.AudioPipelineOutput"),d(V,"class","relative group"),d(Z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(se,"id","diffusers.ImagePipelineOutput"),d(se,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),d(se,"href","#diffusers.ImagePipelineOutput"),d(X,"class","relative group"),d(R,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(te,"id","diffusers.Mel"),d(te,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),d(te,"href","#diffusers.Mel"),d(B,"class","relative group"),d(re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(ie,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(ae,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(le,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(de,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),d(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,u){s(document.head,f),g(e,A,u),g(e,h,u),s(h,p),s(p,D),v(i,D,null),s(h,_),s(h,U),s(U,L),g(e,J,u),g(e,N,u),s(N,G),s(G,Ns),s(N,Gs),g(e,ns,u),g(e,C,u),s(C,Us),s(C,fe),s(fe,Ls),s(C,Ws),g(e,as,u),v(F,e,u),g(e,ls,u),g(e,W,u),s(W,z),s(z,Se),v(pe,Se,null),s(W,Vs),s(W,je),s(je,Zs),g(e,ds,u),g(e,x,u),v(ue,x,null),s(x,Xs),s(x,Ne),s(Ne,Rs),s(x,Bs),s(x,ce),s(ce,Cs),s(ce,Je),s(Je,Fs),s(ce,zs),s(x,Qs),s(x,E),v(me,E,null),s(E,Os),s(E,Ge),s(Ge,qs),s(E,Ys),s(E,Ue),s(Ue,Hs),s(E,Ks),v(Q,E,null),s(E,et),v(O,E,null),s(E,st),v(q,E,null),s(x,tt),s(x,Y),v(he,Y,null),s(Y,rt),s(Y,Le),s(Le,ot),s(x,it),s(x,H),v(ge,H,null),s(H,nt),s(H,We),s(We,at),s(x,lt),s(x,K),v(_e,K,null),s(K,dt),s(K,Ve),s(Ve,ft),g(e,fs,u),g(e,V,u),s(V,ee),s(ee,Ze),v(be,Ze,null),s(V,pt),s(V,Xe),s(Xe,ut),g(e,ps,u),g(e,Z,u),v($e,Z,null),s(Z,ct),s(Z,Re),s(Re,mt),g(e,us,u),g(e,X,u),s(X,se),s(se,Be),v(ve,Be,null),s(X,ht),s(X,Ce),s(Ce,gt),g(e,cs,u),g(e,R,u),v(ye,R,null),s(R,_t),s(R,Fe),s(Fe,bt),g(e,ms,u),g(e,B,u),s(B,te),s(te,ze),v(we,ze,null),s(B,$t),s(B,Qe),s(Qe,vt),g(e,hs,u),g(e,P,u),v(Me,P,null),s(P,yt),s(P,re),v(De,re,null),s(re,wt),s(re,Oe),s(Oe,Mt),s(P,Dt),s(P,oe),v(Pe,oe,null),s(oe,Pt),s(oe,qe),s(qe,At),s(P,xt),s(P,ie),v(Ae,ie,null),s(ie,Et),s(ie,Ye),s(Ye,kt),s(P,It),s(P,ne),v(xe,ne,null),s(ne,Tt),s(ne,He),s(He,Jt),s(P,St),s(P,ae),v(Ee,ae,null),s(ae,jt),s(ae,Ke),s(Ke,Nt),s(P,Gt),s(P,le),v(ke,le,null),s(le,Ut),s(le,es),s(es,Lt),s(P,Wt),s(P,de),v(Ie,de,null),s(de,Vt),s(de,ss),s(ss,Zt),gs=!0},p(e,[u]){const Te={};u&2&&(Te.$$scope={dirty:u,ctx:e}),F.$set(Te);const ts={};u&2&&(ts.$$scope={dirty:u,ctx:e}),Q.$set(ts);const rs={};u&2&&(rs.$$scope={dirty:u,ctx:e}),O.$set(rs);const os={};u&2&&(os.$$scope={dirty:u,ctx:e}),q.$set(os)},i(e){gs||(y(i.$$.fragment,e),y(F.$$.fragment,e),y(pe.$$.fragment,e),y(ue.$$.fragment,e),y(me.$$.fragment,e),y(Q.$$.fragment,e),y(O.$$.fragment,e),y(q.$$.fragment,e),y(he.$$.fragment,e),y(ge.$$.fragment,e),y(_e.$$.fragment,e),y(be.$$.fragment,e),y($e.$$.fragment,e),y(ve.$$.fragment,e),y(ye.$$.fragment,e),y(we.$$.fragment,e),y(Me.$$.fragment,e),y(De.$$.fragment,e),y(Pe.$$.fragment,e),y(Ae.$$.fragment,e),y(xe.$$.fragment,e),y(Ee.$$.fragment,e),y(ke.$$.fragment,e),y(Ie.$$.fragment,e),gs=!0)},o(e){w(i.$$.fragment,e),w(F.$$.fragment,e),w(pe.$$.fragment,e),w(ue.$$.fragment,e),w(me.$$.fragment,e),w(Q.$$.fragment,e),w(O.$$.fragment,e),w(q.$$.fragment,e),w(he.$$.fragment,e),w(ge.$$.fragment,e),w(_e.$$.fragment,e),w(be.$$.fragment,e),w($e.$$.fragment,e),w(ve.$$.fragment,e),w(ye.$$.fragment,e),w(we.$$.fragment,e),w(Me.$$.fragment,e),w(De.$$.fragment,e),w(Pe.$$.fragment,e),w(Ae.$$.fragment,e),w(xe.$$.fragment,e),w(Ee.$$.fragment,e),w(ke.$$.fragment,e),w(Ie.$$.fragment,e),gs=!1},d(e){t(f),e&&t(A),e&&t(h),M(i),e&&t(J),e&&t(N),e&&t(ns),e&&t(C),e&&t(as),M(F,e),e&&t(ls),e&&t(W),M(pe),e&&t(ds),e&&t(x),M(ue),M(me),M(Q),M(O),M(q),M(he),M(ge),M(_e),e&&t(fs),e&&t(V),M(be),e&&t(ps),e&&t(Z),M($e),e&&t(us),e&&t(X),M(ve),e&&t(cs),e&&t(R),M(ye),e&&t(ms),e&&t(B),M(we),e&&t(hs),e&&t(P),M(Me),M(De),M(Pe),M(Ae),M(xe),M(Ee),M(ke),M(Ie)}}}const Sr={local:"audio-diffusion",sections:[{local:"diffusers.AudioDiffusionPipeline",title:"AudioDiffusionPipeline"},{local:"diffusers.AudioPipelineOutput",title:"AudioPipelineOutput"},{local:"diffusers.ImagePipelineOutput",title:"ImagePipelineOutput"},{local:"diffusers.Mel",title:"Mel"}],title:"Audio Diffusion"};function jr(j){return Ar(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Zr extends wr{constructor(f){super();Mr(this,f,jr,Jr,Dr,{})}}export{Zr as default,Sr as metadata};