Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers.js /pr_1649 /en /api /utils /audio.html

HuggingFaceDocBuilder

27 days ago

download

raw

74.7 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"utils/audio","local":"utilsaudio","sections":[{"title":"utils/audio.RawAudio","local":"utilsaudiorawaudio","sections":[{"title":"new RawAudio(audio, sampling_rate)","local":"new-rawaudioaudio-samplingrate","sections":[],"depth":3},{"title":"rawAudio.data ⇒ Float32Array","local":"rawaudiodata--float32array","sections":[],"depth":3},{"title":"rawAudio.toBlob() ⇒ Blob","local":"rawaudiotoblob--blob","sections":[],"depth":3},{"title":"rawAudio.save(path) ⇒ Promise. < void >","local":"rawaudiosavepath--promise--void-","sections":[],"depth":3}],"depth":2},{"title":"<del> utils/audio.read_audio </del>","local":"del-utilsaudioreadaudio-del","sections":[],"depth":2},{"title":"utils/audio.load_audio(url, sampling_rate) ⇒ Promise. < Float32Array >","local":"utilsaudioloadaudiourl-samplingrate--promise--float32array-","sections":[{"title":"load_audio~audio : Float32Array","local":"loadaudioaudio--float32array","sections":[],"depth":3}],"depth":2},{"title":"utils/audio.hanning(M) ⇒ Float64Array","local":"utilsaudiohanningm--float64array","sections":[],"depth":2},{"title":"utils/audio.hamming(M) ⇒ Float64Array","local":"utilsaudiohammingm--float64array","sections":[],"depth":2},{"title":"utils/audio.mel_filter_bank(num_frequency_bins, num_mel_filters, min_frequency, max_frequency, sampling_rate, [norm], [mel_scale], [triangularize_in_mel_space]) ⇒ Array","local":"utilsaudiomelfilterbanknumfrequencybins-nummelfilters-minfrequency-maxfrequency-samplingrate-norm-melscale-triangularizeinmelspace--array","sections":[],"depth":2},{"title":"utils/audio.spectrogram(waveform, window, frame_length, hop_length, options) ⇒ Promise. < Tensor >","local":"utilsaudiospectrogramwaveform-window-framelength-hoplength-options--promise--tensor-","sections":[],"depth":2},{"title":"utils/audio.window_function(window_length, name, options) ⇒ Float64Array","local":"utilsaudiowindowfunctionwindowlength-name-options--float64array","sections":[],"depth":2},{"title":"utils/audio~generalized_cosine_window(M, a_0) ⇒ Float64Array","local":"utilsaudiogeneralizedcosinewindowm-a0--float64array","sections":[],"depth":2},{"title":"utils/audio~hertz_to_mel(freq, [mel_scale]) ⇒ T","local":"utilsaudiohertztomelfreq-melscale--t","sections":[],"depth":2},{"title":"utils/audio~mel_to_hertz(mels, [mel_scale]) ⇒ T","local":"utilsaudiomeltohertzmels-melscale--t","sections":[],"depth":2},{"title":"utils/audio~_create_triangular_filter_bank(fft_freqs, filter_freqs) ⇒ Array","local":"utilsaudiocreatetriangularfilterbankfftfreqs-filterfreqs--array","sections":[],"depth":2},{"title":"utils/audio~linspace(start, end, num) ⇒","local":"utilsaudiolinspacestart-end-num-","sections":[],"depth":2},{"title":"utils/audio~padReflect(array, left, right) ⇒ T","local":"utilsaudiopadreflectarray-left-right--t","sections":[],"depth":2},{"title":"utils/audio~_db_conversion_helper(spectrogram, factor, reference, min_value, db_range) ⇒ T","local":"utilsaudiodbconversionhelperspectrogram-factor-reference-minvalue-dbrange--t","sections":[],"depth":2},{"title":"utils/audio~amplitude_to_db(spectrogram, [reference], [min_value], [db_range]) ⇒ T","local":"utilsaudioamplitudetodbspectrogram-reference-minvalue-dbrange--t","sections":[],"depth":2},{"title":"utils/audio~power_to_db(spectrogram, [reference], [min_value], [db_range]) ⇒ T","local":"utilsaudiopowertodbspectrogram-reference-minvalue-dbrange--t","sections":[],"depth":2},{"title":"utils/audio~encodeWAV(chunks, rate) ⇒ Blob","local":"utilsaudioencodewavchunks-rate--blob","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers.js/pr_1649/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/entry/start.5f753a22.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/scheduler.6efaaf90.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/singletons.c0807d75.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/paths.c5938264.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/entry/app.db3dfcb7.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/preload-helper.1d8e1e5d.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/index.eb3e1f0f.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/nodes/0.1b727385.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/nodes/16.b8a4d970.js">
	<link rel="modulepreload" href="/docs/transformers.js/pr_1649/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.16f13047.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"utils/audio","local":"utilsaudio","sections":[{"title":"utils/audio.RawAudio","local":"utilsaudiorawaudio","sections":[{"title":"new RawAudio(audio, sampling_rate)","local":"new-rawaudioaudio-samplingrate","sections":[],"depth":3},{"title":"rawAudio.data ⇒ Float32Array","local":"rawaudiodata--float32array","sections":[],"depth":3},{"title":"rawAudio.toBlob() ⇒ Blob","local":"rawaudiotoblob--blob","sections":[],"depth":3},{"title":"rawAudio.save(path) ⇒ Promise. < void >","local":"rawaudiosavepath--promise--void-","sections":[],"depth":3}],"depth":2},{"title":"<del> utils/audio.read_audio </del>","local":"del-utilsaudioreadaudio-del","sections":[],"depth":2},{"title":"utils/audio.load_audio(url, sampling_rate) ⇒ Promise. < Float32Array >","local":"utilsaudioloadaudiourl-samplingrate--promise--float32array-","sections":[{"title":"load_audio~audio : Float32Array","local":"loadaudioaudio--float32array","sections":[],"depth":3}],"depth":2},{"title":"utils/audio.hanning(M) ⇒ Float64Array","local":"utilsaudiohanningm--float64array","sections":[],"depth":2},{"title":"utils/audio.hamming(M) ⇒ Float64Array","local":"utilsaudiohammingm--float64array","sections":[],"depth":2},{"title":"utils/audio.mel_filter_bank(num_frequency_bins, num_mel_filters, min_frequency, max_frequency, sampling_rate, [norm], [mel_scale], [triangularize_in_mel_space]) ⇒ Array","local":"utilsaudiomelfilterbanknumfrequencybins-nummelfilters-minfrequency-maxfrequency-samplingrate-norm-melscale-triangularizeinmelspace--array","sections":[],"depth":2},{"title":"utils/audio.spectrogram(waveform, window, frame_length, hop_length, options) ⇒ Promise. < Tensor >","local":"utilsaudiospectrogramwaveform-window-framelength-hoplength-options--promise--tensor-","sections":[],"depth":2},{"title":"utils/audio.window_function(window_length, name, options) ⇒ Float64Array","local":"utilsaudiowindowfunctionwindowlength-name-options--float64array","sections":[],"depth":2},{"title":"utils/audio~generalized_cosine_window(M, a_0) ⇒ Float64Array","local":"utilsaudiogeneralizedcosinewindowm-a0--float64array","sections":[],"depth":2},{"title":"utils/audio~hertz_to_mel(freq, [mel_scale]) ⇒ T","local":"utilsaudiohertztomelfreq-melscale--t","sections":[],"depth":2},{"title":"utils/audio~mel_to_hertz(mels, [mel_scale]) ⇒ T","local":"utilsaudiomeltohertzmels-melscale--t","sections":[],"depth":2},{"title":"utils/audio~_create_triangular_filter_bank(fft_freqs, filter_freqs) ⇒ Array","local":"utilsaudiocreatetriangularfilterbankfftfreqs-filterfreqs--array","sections":[],"depth":2},{"title":"utils/audio~linspace(start, end, num) ⇒","local":"utilsaudiolinspacestart-end-num-","sections":[],"depth":2},{"title":"utils/audio~padReflect(array, left, right) ⇒ T","local":"utilsaudiopadreflectarray-left-right--t","sections":[],"depth":2},{"title":"utils/audio~_db_conversion_helper(spectrogram, factor, reference, min_value, db_range) ⇒ T","local":"utilsaudiodbconversionhelperspectrogram-factor-reference-minvalue-dbrange--t","sections":[],"depth":2},{"title":"utils/audio~amplitude_to_db(spectrogram, [reference], [min_value], [db_range]) ⇒ T","local":"utilsaudioamplitudetodbspectrogram-reference-minvalue-dbrange--t","sections":[],"depth":2},{"title":"utils/audio~power_to_db(spectrogram, [reference], [min_value], [db_range]) ⇒ T","local":"utilsaudiopowertodbspectrogram-reference-minvalue-dbrange--t","sections":[],"depth":2},{"title":"utils/audio~encodeWAV(chunks, rate) ⇒ Blob","local":"utilsaudioencodewavchunks-rate--blob","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <a id="module_utils/audio" class="group"></a> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="utilsaudio" 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" href="#utilsaudio"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio</span></h1> <p data-svelte-h="svelte-1u3vk4m">Helper module for audio processing.</p> <p data-svelte-h="svelte-il3kl8">These functions and classes are only used internally,
	meaning an end-user shouldn’t need to access anything here.</p> <ul data-svelte-h="svelte-1lyp1qg"><li><a href="#module_utils/audio">utils/audio</a> <ul><li><em>static</em> <ul><li><a href="#module_utils/audio.RawAudio">.RawAudio</a> <ul><li><a href="#new_module_utils/audio.RawAudio_new"><code>new RawAudio(audio, sampling_rate)</code></a></li> <li><a href="#module_utils/audio.RawAudio+data"><code>.data</code></a> ⇒ <code>Float32Array</code></li> <li><a href="#module_utils/audio.RawAudio+toBlob"><code>.toBlob()</code></a> ⇒ <code>Blob</code></li> <li><a href="#module_utils/audio.RawAudio+save"><code>.save(path)</code></a> ⇒ <code>Promise.<void></code></li></ul></li> <li><del>[`.read_audio`](#module_utils/audio.read_audio)</del></li> <li><a href="#module_utils/audio.load_audio"><code>.load_audio(url, sampling_rate)</code></a> ⇒ <code>Promise.<Float32Array></code> <ul><li><a href="#module_utils/audio.load_audio..audio"><code>~audio</code></a> : <code>Float32Array</code></li></ul></li> <li><a href="#module_utils/audio.hanning"><code>.hanning(M)</code></a> ⇒ <code>Float64Array</code></li> <li><a href="#module_utils/audio.hamming"><code>.hamming(M)</code></a> ⇒ <code>Float64Array</code></li> <li><a href="#module_utils/audio.mel_filter_bank"><code>.mel_filter_bank(num_frequency_bins, num_mel_filters, min_frequency, max_frequency, sampling_rate, [norm], [mel_scale], [triangularize_in_mel_space])</code></a> ⇒ <code>Array</code></li> <li><a href="#module_utils/audio.spectrogram"><code>.spectrogram(waveform, window, frame_length, hop_length, options)</code></a> ⇒ <a href="#Tensor"><code>Promise.<Tensor></code></a></li> <li><a href="#module_utils/audio.window_function"><code>.window_function(window_length, name, options)</code></a> ⇒ <code>Float64Array</code></li></ul></li> <li><em>inner</em> <ul><li><a href="#module_utils/audio..generalized_cosine_window"><code>~generalized_cosine_window(M, a_0)</code></a> ⇒ <code>Float64Array</code></li> <li><a href="#module_utils/audio..hertz_to_mel"><code>~hertz_to_mel(freq, [mel_scale])</code></a> ⇒ <code>T</code></li> <li><a href="#module_utils/audio..mel_to_hertz"><code>~mel_to_hertz(mels, [mel_scale])</code></a> ⇒ <code>T</code></li> <li><a href="#module_utils/audio.._create_triangular_filter_bank"><code>~_create_triangular_filter_bank(fft_freqs, filter_freqs)</code></a> ⇒ <code>Array</code></li> <li><a href="#module_utils/audio..linspace"><code>~linspace(start, end, num)</code></a> ⇒</li> <li><a href="#module_utils/audio..padReflect"><code>~padReflect(array, left, right)</code></a> ⇒ <code>T</code></li> <li><a href="#module_utils/audio.._db_conversion_helper"><code>~_db_conversion_helper(spectrogram, factor, reference, min_value, db_range)</code></a> ⇒ <code>T</code></li> <li><a href="#module_utils/audio..amplitude_to_db"><code>~amplitude_to_db(spectrogram, [reference], [min_value], [db_range])</code></a> ⇒ <code>T</code></li> <li><a href="#module_utils/audio..power_to_db"><code>~power_to_db(spectrogram, [reference], [min_value], [db_range])</code></a> ⇒ <code>T</code></li> <li><a href="#module_utils/audio..encodeWAV"><code>~encodeWAV(chunks, rate)</code></a> ⇒ <code>Blob</code></li></ul></li></ul></li></ul> <hr> <a id="module_utils/audio.RawAudio" class="group"></a> <h2 class="relative group"><a id="utilsaudiorawaudio" 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" href="#utilsaudiorawaudio"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.RawAudio</span></h2> <p data-svelte-h="svelte-1s2dpoa"><strong>Kind</strong>: static class of <a href="#module_utils/audio"><code>utils/audio</code></a></p> <ul data-svelte-h="svelte-1dx877j"><li><a href="#module_utils/audio.RawAudio">.RawAudio</a> <ul><li><a href="#new_module_utils/audio.RawAudio_new"><code>new RawAudio(audio, sampling_rate)</code></a></li> <li><a href="#module_utils/audio.RawAudio+data"><code>.data</code></a> ⇒ <code>Float32Array</code></li> <li><a href="#module_utils/audio.RawAudio+toBlob"><code>.toBlob()</code></a> ⇒ <code>Blob</code></li> <li><a href="#module_utils/audio.RawAudio+save"><code>.save(path)</code></a> ⇒ <code>Promise.<void></code></li></ul></li></ul> <hr> <a id="new_module_utils/audio.RawAudio_new" class="group"></a> <h3 class="relative group"><a id="new-rawaudioaudio-samplingrate" 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" href="#new-rawaudioaudio-samplingrate"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>new RawAudio(audio, sampling_rate)</span></h3> <p data-svelte-h="svelte-1a89sw5">Create a new <code>RawAudio</code> object.</p> <table data-svelte-h="svelte-90rnkj"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>audio</td><td><code>Float32Array</code> \| <code>Array</code></td><td><p>Audio data, either as a single <code>Float32Array</code> chunk or multiple <code>Float32Array</code> chunks.</p></td> </tr><tr><td>sampling_rate</td><td><code>number</code></td><td><p>Sampling rate of the audio data</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.RawAudio+data" class="group"></a> <h3 class="relative group"><a id="rawaudiodata--float32array" 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" href="#rawaudiodata--float32array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>rawAudio.data ⇒ Float32Array</span></h3> <p data-svelte-h="svelte-3yy9bz">Get the audio data, accumulating all chunks if necessary.</p> <p data-svelte-h="svelte-1ujh659"><strong>Kind</strong>: instance property of <a href="#module_utils/audio.RawAudio"><code>RawAudio</code></a><br> <strong>Returns</strong>: <code>Float32Array</code> - The audio data.</p> <hr> <a id="module_utils/audio.RawAudio+toBlob" class="group"></a> <h3 class="relative group"><a id="rawaudiotoblob--blob" 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" href="#rawaudiotoblob--blob"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>rawAudio.toBlob() ⇒ Blob</span></h3> <p data-svelte-h="svelte-m879bd">Convert the audio to a blob.</p> <p data-svelte-h="svelte-ugrjp2"><strong>Kind</strong>: instance method of <a href="#module_utils/audio.RawAudio"><code>RawAudio</code></a></p> <hr> <a id="module_utils/audio.RawAudio+save" class="group"></a> <h3 class="relative group"><a id="rawaudiosavepath--promise--void-" 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" href="#rawaudiosavepath--promise--void-"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>rawAudio.save(path) ⇒ Promise. < void ></span></h3> <p data-svelte-h="svelte-10oc88s">Save the audio to a wav file.</p> <p data-svelte-h="svelte-ugrjp2"><strong>Kind</strong>: instance method of <a href="#module_utils/audio.RawAudio"><code>RawAudio</code></a></p> <table data-svelte-h="svelte-f03x1m"><thead><tr><th>Param</th><th>Type</th></tr></thead> <tbody><tr><td>path</td><td><code>string</code></td></tr></tbody></table> <hr> <a id="module_utils/audio.read_audio" class="group"></a> <h2 class="relative group"><a id="del-utilsaudioreadaudio-del" 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" href="#del-utilsaudioreadaudio-del"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span><del> utils/audio.read_audio </del></span></h2> <p data-svelte-h="svelte-b46hp8"><strong><em>Use <a href="load_audio">load_audio</a> instead.</em></strong></p> <p data-svelte-h="svelte-1tn0kms"><strong>Kind</strong>: static constant of <a href="#module_utils/audio"><code>utils/audio</code></a></p> <hr> <a id="module_utils/audio.load_audio" class="group"></a> <h2 class="relative group"><a id="utilsaudioloadaudiourl-samplingrate--promise--float32array-" 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" href="#utilsaudioloadaudiourl-samplingrate--promise--float32array-"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.load_audio(url, sampling_rate) ⇒ Promise. < Float32Array ></span></h2> <p data-svelte-h="svelte-151kq4z">Helper function to load audio from a path/URL.</p> <p data-svelte-h="svelte-wzwr9x"><strong>Kind</strong>: static method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Promise.<Float32Array></code> - The decoded audio as a <code>Float32Array</code>.</p> <table data-svelte-h="svelte-1u23bjg"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>url</td><td><code>string</code> \| <code>URL</code></td><td><p>The path/URL to load the audio from.</p></td> </tr><tr><td>sampling_rate</td><td><code>number</code></td><td><p>The sampling rate to use when decoding the audio.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.load_audio..audio" class="group"></a> <h3 class="relative group"><a id="loadaudioaudio--float32array" 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" href="#loadaudioaudio--float32array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>load_audio~audio : Float32Array</span></h3> <p data-svelte-h="svelte-vz2lqx"><strong>Kind</strong>: inner property of <a href="#module_utils/audio.load_audio"><code>load_audio</code></a></p> <hr> <a id="module_utils/audio.hanning" class="group"></a> <h2 class="relative group"><a id="utilsaudiohanningm--float64array" 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" href="#utilsaudiohanningm--float64array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.hanning(M) ⇒ Float64Array</span></h2> <p data-svelte-h="svelte-13ns2vg">Generates a Hanning window of length M.
	See <a href="https://numpy.org/doc/stable/reference/generated/numpy.hanning.html" rel="nofollow">https://numpy.org/doc/stable/reference/generated/numpy.hanning.html</a> for more information.</p> <p data-svelte-h="svelte-187ugov"><strong>Kind</strong>: static method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Float64Array</code> - The generated Hanning window.</p> <table data-svelte-h="svelte-1x4zay3"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>M</td><td><code>number</code></td><td><p>The length of the Hanning window to generate.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.hamming" class="group"></a> <h2 class="relative group"><a id="utilsaudiohammingm--float64array" 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" href="#utilsaudiohammingm--float64array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.hamming(M) ⇒ Float64Array</span></h2> <p data-svelte-h="svelte-8gymva">Generates a Hamming window of length M.
	See <a href="https://numpy.org/doc/stable/reference/generated/numpy.hamming.html" rel="nofollow">https://numpy.org/doc/stable/reference/generated/numpy.hamming.html</a> for more information.</p> <p data-svelte-h="svelte-1dyre01"><strong>Kind</strong>: static method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Float64Array</code> - The generated Hamming window.</p> <table data-svelte-h="svelte-io80jx"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>M</td><td><code>number</code></td><td><p>The length of the Hamming window to generate.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.mel_filter_bank" class="group"></a> <h2 class="relative group"><a id="utilsaudiomelfilterbanknumfrequencybins-nummelfilters-minfrequency-maxfrequency-samplingrate-norm-melscale-triangularizeinmelspace--array" 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" href="#utilsaudiomelfilterbanknumfrequencybins-nummelfilters-minfrequency-maxfrequency-samplingrate-norm-melscale-triangularizeinmelspace--array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.mel_filter_bank(num_frequency_bins, num_mel_filters, min_frequency, max_frequency, sampling_rate, [norm], [mel_scale], [triangularize_in_mel_space]) ⇒ Array</span></h2> <p data-svelte-h="svelte-ke4v6b">Creates a frequency bin conversion matrix used to obtain a mel spectrogram. This is called a <em>mel filter bank</em>, and
	various implementation exist, which differ in the number of filters, the shape of the filters, the way the filters
	are spaced, the bandwidth of the filters, and the manner in which the spectrum is warped. The goal of these
	features is to approximate the non-linear human perception of the variation in pitch with respect to the frequency.</p> <p data-svelte-h="svelte-1td0sb4"><strong>Kind</strong>: static method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Array</code> - Triangular filter bank matrix, which is a 2D array of shape (<code>num_frequency_bins</code>, <code>num_mel_filters</code>).
	This is a projection matrix to go from a spectrogram to a mel spectrogram.</p> <table data-svelte-h="svelte-vzsu9f"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>num_frequency_bins</td><td><code>number</code></td><td><p>Number of frequency bins (should be the same as <code>n_fft // 2 + 1</code>
	where <code>n_fft</code> is the size of the Fourier Transform used to compute the spectrogram).</p></td> </tr><tr><td>num_mel_filters</td><td><code>number</code></td><td><p>Number of mel filters to generate.</p></td> </tr><tr><td>min_frequency</td><td><code>number</code></td><td><p>Lowest frequency of interest in Hz.</p></td> </tr><tr><td>max_frequency</td><td><code>number</code></td><td><p>Highest frequency of interest in Hz. This should not exceed <code>sampling_rate / 2</code>.</p></td> </tr><tr><td>sampling_rate</td><td><code>number</code></td><td><p>Sample rate of the audio waveform.</p></td> </tr><tr><td>[norm]</td><td><code>string</code> \| <code>null</code></td><td><p>If <code>"slaney"</code>, divide the triangular mel weights by the width of the mel band (area normalization).</p></td> </tr><tr><td>[mel_scale]</td><td><code>string</code></td><td><p>The mel frequency scale to use, <code>"htk"</code> or <code>"slaney"</code>.</p></td> </tr><tr><td>[triangularize_in_mel_space]</td><td><code>boolean</code></td><td><p>If this option is enabled, the triangular filter is applied in mel space rather than frequency space.
	This should be set to <code>true</code> in order to get the same results as <code>torchaudio</code> when computing mel filters.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.spectrogram" class="group"></a> <h2 class="relative group"><a id="utilsaudiospectrogramwaveform-window-framelength-hoplength-options--promise--tensor-" 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" href="#utilsaudiospectrogramwaveform-window-framelength-hoplength-options--promise--tensor-"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.spectrogram(waveform, window, frame_length, hop_length, options) ⇒ Promise. < Tensor ></span></h2> <p data-svelte-h="svelte-10mwufd">Calculates a spectrogram over one waveform using the Short-Time Fourier Transform.</p> <p data-svelte-h="svelte-zfp2ya">This function can create the following kinds of spectrograms:</p> <ul data-svelte-h="svelte-14mziv8"><li>amplitude spectrogram (<code>power = 1.0</code>)</li> <li>power spectrogram (<code>power = 2.0</code>)</li> <li>complex-valued spectrogram (<code>power = None</code>)</li> <li>log spectrogram (use <code>log_mel</code> argument)</li> <li>mel spectrogram (provide <code>mel_filters</code>)</li> <li>log-mel spectrogram (provide <code>mel_filters</code> and <code>log_mel</code>)</li></ul> <p data-svelte-h="svelte-iwx6w9">In this implementation, the window is assumed to be zero-padded to have the same size as the analysis frame.
	A padded window can be obtained from <code>window_function()</code>. The FFT input buffer may be larger than the analysis frame,
	typically the next power of two.</p> <p data-svelte-h="svelte-1shoq4k"><strong>Kind</strong>: static method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <a href="#Tensor"><code>Promise.<Tensor></code></a> - Spectrogram of shape <code>(num_frequency_bins, length)</code> (regular spectrogram) or shape <code>(num_mel_filters, length)</code> (mel spectrogram).</p> <table data-svelte-h="svelte-1vbe6de"><thead><tr><th>Param</th><th>Type</th><th>Default</th><th>Description</th></tr></thead> <tbody><tr><td>waveform</td><td><code>Float32Array</code> \| <code>Float64Array</code></td><td></td><td><p>The input waveform of shape <code>(length,)</code>. This must be a single real-valued, mono waveform.</p></td> </tr><tr><td>window</td><td><code>Float32Array</code> \| <code>Float64Array</code></td><td></td><td><p>The windowing function to apply of shape <code>(frame_length,)</code>, including zero-padding if necessary. The actual window length may be
	shorter than <code>frame_length</code>, but we're assuming the array has already been zero-padded.</p></td> </tr><tr><td>frame_length</td><td><code>number</code></td><td></td><td><p>The length of the analysis frames in samples (a.k.a., <code>fft_length</code>).</p></td> </tr><tr><td>hop_length</td><td><code>number</code></td><td></td><td><p>The stride between successive analysis frames in samples.</p></td> </tr><tr><td>options</td><td><code>Object</code></td><td></td><td></td> </tr><tr><td>[options.fft_length]</td><td><code>number</code></td><td><code></code></td><td><p>The size of the FFT buffer in samples. This determines how many frequency bins the spectrogram will have.
	For optimal speed, this should be a power of two. If <code>null</code>, uses <code>frame_length</code>.</p></td> </tr><tr><td>[options.power]</td><td><code>number</code></td><td><code>1.0</code></td><td><p>If 1.0, returns the amplitude spectrogram. If 2.0, returns the power spectrogram. If <code>null</code>, returns complex numbers.</p></td> </tr><tr><td>[options.center]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to pad the waveform so that frame <code>t</code> is centered around time <code>t * hop_length</code>. If <code>false</code>, frame
	<code>t</code> will start at time <code>t * hop_length</code>.</p></td> </tr><tr><td>[options.pad_mode]</td><td><code>string</code></td><td><code>""reflect""</code></td><td><p>Padding mode used when <code>center</code> is <code>true</code>. Possible values are: <code>"constant"</code> (pad with zeros),
	<code>"edge"</code> (pad with edge values), <code>"reflect"</code> (pads with mirrored values).</p></td> </tr><tr><td>[options.onesided]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>If <code>true</code>, only computes the positive frequencies and returns a spectrogram containing <code>fft_length // 2 + 1</code>
	frequency bins. If <code>false</code>, also computes the negative frequencies and returns <code>fft_length</code> frequency bins.</p></td> </tr><tr><td>[options.preemphasis]</td><td><code>number</code></td><td><code></code></td><td><p>Coefficient for a low-pass filter that applies pre-emphasis before the DFT.</p></td> </tr><tr><td>[options.preemphasis_htk_flavor]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to apply the pre-emphasis filter in the HTK flavor.</p></td> </tr><tr><td>[options.mel_filters]</td><td><code>Array</code></td><td><code></code></td><td><p>The mel filter bank of shape <code>(num_freq_bins, num_mel_filters)</code>.
	If supplied, applies this filter bank to create a mel spectrogram.</p></td> </tr><tr><td>[options.mel_floor]</td><td><code>number</code></td><td><code>1e-10</code></td><td><p>Minimum value of mel frequency banks.</p></td> </tr><tr><td>[options.log_mel]</td><td><code>string</code></td><td><code>null</code></td><td><p>How to convert the spectrogram to log scale. Possible options are:
	<code>null</code> (don't convert), <code>"log"</code> (take the natural logarithm), <code>"log10"</code> (take the base-10 logarithm), <code>"dB"</code> (convert to decibels),
	<code>"log10_max_norm"</code> (take <code>log10</code>, then apply <code>(max(x, maxVal - 8) + 4) / 4</code> normalization, where <code>maxVal</code> is computed from data or given by <code>max_log_mel</code>).
	Can only be used when <code>power</code> is not <code>null</code>.</p></td> </tr><tr><td>[options.max_log_mel]</td><td><code>number</code></td><td><code></code></td><td><p>When <code>log_mel</code> is <code>"log10_max_norm"</code>, use this fixed value as the max instead of computing from data.</p></td> </tr><tr><td>[options.reference]</td><td><code>number</code></td><td><code>1.0</code></td><td><p>Sets the input spectrogram value that corresponds to 0 dB. For example, use <code>max(spectrogram)[0]</code> to set
	the loudest part to 0 dB. Must be greater than zero.</p></td> </tr><tr><td>[options.min_value]</td><td><code>number</code></td><td><code>1e-10</code></td><td><p>The spectrogram will be clipped to this minimum value before conversion to decibels, to avoid taking <code>log(0)</code>.
	For a power spectrogram, the default of <code>1e-10</code> corresponds to a minimum of -100 dB. For an amplitude spectrogram, the value <code>1e-5</code> corresponds to -100 dB.
	Must be greater than zero.</p></td> </tr><tr><td>[options.db_range]</td><td><code>number</code></td><td><code></code></td><td><p>Sets the maximum dynamic range in decibels. For example, if <code>db_range = 80</code>, the difference between the
	peak value and the smallest value will never be more than 80 dB. Must be greater than zero.</p></td> </tr><tr><td>[options.remove_dc_offset]</td><td><code>boolean</code></td><td><code></code></td><td><p>Subtract mean from waveform on each frame, applied before pre-emphasis. This should be set to <code>true</code> in
	order to get the same results as <code>torchaudio.compliance.kaldi.fbank</code> when computing mel filters.</p></td> </tr><tr><td>[options.max_num_frames]</td><td><code>number</code></td><td><code></code></td><td><p>If provided, limits the number of frames to compute to this value.</p></td> </tr><tr><td>[options.min_num_frames]</td><td><code>number</code></td><td><code></code></td><td><p>If provided, ensures the number of frames to compute is at least this value.</p></td> </tr><tr><td>[options.do_pad]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>If <code>true</code>, pads the output spectrogram to have <code>max_num_frames</code> frames.</p></td> </tr><tr><td>[options.transpose]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>If <code>true</code>, the returned spectrogram will have shape <code>(num_frames, num_frequency_bins/num_mel_filters)</code>. If <code>false</code>, the returned spectrogram will have shape <code>(num_frequency_bins/num_mel_filters, num_frames)</code>.</p></td> </tr><tr><td>[options.mel_offset]</td><td><code>number</code></td><td><code>0</code></td><td><p>Offset to add to the mel spectrogram to avoid taking the log of zero.</p></td> </tr><tr><td>[options.mel_floor_mode]</td><td><code>string</code></td><td><code>""clamp""</code></td><td><p>If <code>mel_offset</code> is provided, this option determines how to apply it. If <code>"clamp"</code>, the mel spectrogram will be clamped to have a minimum value of <code>mel_offset</code>. If <code>"add"</code>, <code>mel_offset</code> will be added to all values of the mel spectrogram.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.window_function" class="group"></a> <h2 class="relative group"><a id="utilsaudiowindowfunctionwindowlength-name-options--float64array" 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" href="#utilsaudiowindowfunctionwindowlength-name-options--float64array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio.window_function(window_length, name, options) ⇒ Float64Array</span></h2> <p data-svelte-h="svelte-13l1rbm">Returns an array containing the specified window.</p> <p data-svelte-h="svelte-9ixqdv"><strong>Kind</strong>: static method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Float64Array</code> - The window of shape <code>(window_length,)</code> or <code>(frame_length,)</code>.</p> <table data-svelte-h="svelte-h693em"><thead><tr><th>Param</th><th>Type</th><th>Default</th><th>Description</th></tr></thead> <tbody><tr><td>window_length</td><td><code>number</code></td><td></td><td><p>The length of the window in samples.</p></td> </tr><tr><td>name</td><td><code>string</code></td><td></td><td><p>The name of the window function.</p></td> </tr><tr><td>options</td><td><code>Object</code></td><td></td><td><p>Additional options.</p></td> </tr><tr><td>[options.periodic]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether the window is periodic or symmetric.</p></td> </tr><tr><td>[options.frame_length]</td><td><code>number</code></td><td><code></code></td><td><p>The length of the analysis frames in samples.
	Provide a value for <code>frame_length</code> if the window is smaller than the frame length, so that it will be zero-padded.</p></td> </tr><tr><td>[options.center]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to center the window inside the FFT buffer. Only used when <code>frame_length</code> is provided.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio..generalized_cosine_window" class="group"></a> <h2 class="relative group"><a id="utilsaudiogeneralizedcosinewindowm-a0--float64array" 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" href="#utilsaudiogeneralizedcosinewindowm-a0--float64array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~generalized_cosine_window(M, a_0) ⇒ Float64Array</span></h2> <p data-svelte-h="svelte-1lyeqxj">Helper function to generate windows that are special cases of the generalized cosine window.
	See <a href="https://www.mathworks.com/help/signal/ug/generalized-cosine-windows.html" rel="nofollow">https://www.mathworks.com/help/signal/ug/generalized-cosine-windows.html</a> for more information.</p> <p data-svelte-h="svelte-xu9700"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Float64Array</code> - The generated window.</p> <table data-svelte-h="svelte-11w0boh"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>M</td><td><code>number</code></td><td><p>Number of points in the output window. If zero or less, an empty array is returned.</p></td> </tr><tr><td>a_0</td><td><code>number</code></td><td><p>Offset for the generalized cosine window.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio..hertz_to_mel" class="group"></a> <h2 class="relative group"><a id="utilsaudiohertztomelfreq-melscale--t" 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" href="#utilsaudiohertztomelfreq-melscale--t"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~hertz_to_mel(freq, [mel_scale]) ⇒ T</span></h2> <p data-svelte-h="svelte-5cebk5"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a></p> <table data-svelte-h="svelte-1w6ehfm"><thead><tr><th>Param</th><th>Type</th><th>Default</th></tr></thead> <tbody><tr><td>freq</td><td><code>T</code></td><td></td> </tr><tr><td>[mel_scale]</td><td><code>string</code></td><td><code>"htk"</code></td></tr></tbody></table> <hr> <a id="module_utils/audio..mel_to_hertz" class="group"></a> <h2 class="relative group"><a id="utilsaudiomeltohertzmels-melscale--t" 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" href="#utilsaudiomeltohertzmels-melscale--t"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~mel_to_hertz(mels, [mel_scale]) ⇒ T</span></h2> <p data-svelte-h="svelte-5cebk5"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a></p> <table data-svelte-h="svelte-io7ocd"><thead><tr><th>Param</th><th>Type</th><th>Default</th></tr></thead> <tbody><tr><td>mels</td><td><code>T</code></td><td></td> </tr><tr><td>[mel_scale]</td><td><code>string</code></td><td><code>"htk"</code></td></tr></tbody></table> <hr> <a id="module_utils/audio.._create_triangular_filter_bank" class="group"></a> <h2 class="relative group"><a id="utilsaudiocreatetriangularfilterbankfftfreqs-filterfreqs--array" 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" href="#utilsaudiocreatetriangularfilterbankfftfreqs-filterfreqs--array"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~_create_triangular_filter_bank(fft_freqs, filter_freqs) ⇒ Array</span></h2> <p data-svelte-h="svelte-uj0il7">Creates a triangular filter bank.</p> <p data-svelte-h="svelte-srmfwi">Adapted from torchaudio and librosa.</p> <p data-svelte-h="svelte-1stn33f"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Array</code> - of shape <code>(num_frequency_bins, num_mel_filters)</code>.</p> <table data-svelte-h="svelte-2x9dyx"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>fft_freqs</td><td><code>Float64Array</code></td><td><p>Discrete frequencies of the FFT bins in Hz, of shape <code>(num_frequency_bins,)</code>.</p></td> </tr><tr><td>filter_freqs</td><td><code>Float64Array</code></td><td><p>Center frequencies of the triangular filters to create, in Hz, of shape <code>(num_mel_filters,)</code>.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio..linspace" class="group"></a> <h2 class="relative group"><a id="utilsaudiolinspacestart-end-num-" 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" href="#utilsaudiolinspacestart-end-num-"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~linspace(start, end, num) ⇒</span></h2> <p data-svelte-h="svelte-osjtvn">Return evenly spaced numbers over a specified interval.</p> <p data-svelte-h="svelte-bfmjcl"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>num</code> evenly spaced samples, calculated over the interval <code>[start, stop]</code>.</p> <table data-svelte-h="svelte-c7ztlp"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>start</td><td><code>number</code></td><td><p>The starting value of the sequence.</p></td> </tr><tr><td>end</td><td><code>number</code></td><td><p>The end value of the sequence.</p></td> </tr><tr><td>num</td><td><code>number</code></td><td><p>Number of samples to generate.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio..padReflect" class="group"></a> <h2 class="relative group"><a id="utilsaudiopadreflectarray-left-right--t" 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" href="#utilsaudiopadreflectarray-left-right--t"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~padReflect(array, left, right) ⇒ T</span></h2> <p data-svelte-h="svelte-115nnpl"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>T</code> - The padded array.</p> <table data-svelte-h="svelte-6p81mk"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>array</td><td><code>T</code></td><td><p>The array to pad.</p></td> </tr><tr><td>left</td><td><code>number</code></td><td><p>The amount of padding to add to the left.</p></td> </tr><tr><td>right</td><td><code>number</code></td><td><p>The amount of padding to add to the right.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio.._db_conversion_helper" class="group"></a> <h2 class="relative group"><a id="utilsaudiodbconversionhelperspectrogram-factor-reference-minvalue-dbrange--t" 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" href="#utilsaudiodbconversionhelperspectrogram-factor-reference-minvalue-dbrange--t"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~_db_conversion_helper(spectrogram, factor, reference, min_value, db_range) ⇒ T</span></h2> <p data-svelte-h="svelte-9t3wul">Helper function to compute <code>amplitude_to_db</code> and <code>power_to_db</code>.</p> <p data-svelte-h="svelte-5cebk5"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a></p> <table data-svelte-h="svelte-heeupf"><thead><tr><th>Param</th><th>Type</th></tr></thead> <tbody><tr><td>spectrogram</td><td><code>T</code></td> </tr><tr><td>factor</td><td><code>number</code></td> </tr><tr><td>reference</td><td><code>number</code></td> </tr><tr><td>min_value</td><td><code>number</code></td> </tr><tr><td>db_range</td><td><code>number</code></td></tr></tbody></table> <hr> <a id="module_utils/audio..amplitude_to_db" class="group"></a> <h2 class="relative group"><a id="utilsaudioamplitudetodbspectrogram-reference-minvalue-dbrange--t" 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" href="#utilsaudioamplitudetodbspectrogram-reference-minvalue-dbrange--t"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~amplitude_to_db(spectrogram, [reference], [min_value], [db_range]) ⇒ T</span></h2> <p data-svelte-h="svelte-93lmwr">Converts an amplitude spectrogram to the decibel scale. This computes <code>20 * log10(spectrogram / reference)</code>,
	using basic logarithm properties for numerical stability. NOTE: Operates in-place.</p> <p data-svelte-h="svelte-12zo44d">The motivation behind applying the log function on the (mel) spectrogram is that humans do not hear loudness on a
	linear scale. Generally to double the perceived volume of a sound we need to put 8 times as much energy into it.
	This means that large variations in energy may not sound all that different if the sound is loud to begin with.
	This compression operation makes the (mel) spectrogram features match more closely what humans actually hear.</p> <p data-svelte-h="svelte-1d363v6"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>T</code> - The modified spectrogram in decibels.</p> <table data-svelte-h="svelte-1wpe278"><thead><tr><th>Param</th><th>Type</th><th>Default</th><th>Description</th></tr></thead> <tbody><tr><td>spectrogram</td><td><code>T</code></td><td></td><td><p>The input amplitude (mel) spectrogram.</p></td> </tr><tr><td>[reference]</td><td><code>number</code></td><td><code>1.0</code></td><td><p>Sets the input spectrogram value that corresponds to 0 dB.
	For example, use <code>np.max(spectrogram)</code> to set the loudest part to 0 dB. Must be greater than zero.</p></td> </tr><tr><td>[min_value]</td><td><code>number</code></td><td><code>1e-5</code></td><td><p>The spectrogram will be clipped to this minimum value before conversion to decibels,
	to avoid taking <code>log(0)</code>. The default of <code>1e-5</code> corresponds to a minimum of -100 dB. Must be greater than zero.</p></td> </tr><tr><td>[db_range]</td><td><code>number</code></td><td><code></code></td><td><p>Sets the maximum dynamic range in decibels. For example, if <code>db_range = 80</code>, the
	difference between the peak value and the smallest value will never be more than 80 dB. Must be greater than zero.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio..power_to_db" class="group"></a> <h2 class="relative group"><a id="utilsaudiopowertodbspectrogram-reference-minvalue-dbrange--t" 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" href="#utilsaudiopowertodbspectrogram-reference-minvalue-dbrange--t"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~power_to_db(spectrogram, [reference], [min_value], [db_range]) ⇒ T</span></h2> <p data-svelte-h="svelte-1dxatci">Converts a power spectrogram to the decibel scale. This computes <code>10 * log10(spectrogram / reference)</code>,
	using basic logarithm properties for numerical stability. NOTE: Operates in-place.</p> <p data-svelte-h="svelte-12zo44d">The motivation behind applying the log function on the (mel) spectrogram is that humans do not hear loudness on a
	linear scale. Generally to double the perceived volume of a sound we need to put 8 times as much energy into it.
	This means that large variations in energy may not sound all that different if the sound is loud to begin with.
	This compression operation makes the (mel) spectrogram features match more closely what humans actually hear.</p> <p data-svelte-h="svelte-1bxqqp">Based on the implementation of <code>librosa.power_to_db</code>.</p> <p data-svelte-h="svelte-1d363v6"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>T</code> - The modified spectrogram in decibels.</p> <table data-svelte-h="svelte-h9b3kb"><thead><tr><th>Param</th><th>Type</th><th>Default</th><th>Description</th></tr></thead> <tbody><tr><td>spectrogram</td><td><code>T</code></td><td></td><td><p>The input power (mel) spectrogram. Note that a power spectrogram has the amplitudes squared!</p></td> </tr><tr><td>[reference]</td><td><code>number</code></td><td><code>1.0</code></td><td><p>Sets the input spectrogram value that corresponds to 0 dB.
	For example, use <code>np.max(spectrogram)</code> to set the loudest part to 0 dB. Must be greater than zero.</p></td> </tr><tr><td>[min_value]</td><td><code>number</code></td><td><code>1e-10</code></td><td><p>The spectrogram will be clipped to this minimum value before conversion to decibels,
	to avoid taking <code>log(0)</code>. The default of <code>1e-10</code> corresponds to a minimum of -100 dB. Must be greater than zero.</p></td> </tr><tr><td>[db_range]</td><td><code>number</code></td><td><code></code></td><td><p>Sets the maximum dynamic range in decibels. For example, if <code>db_range = 80</code>, the
	difference between the peak value and the smallest value will never be more than 80 dB. Must be greater than zero.</p></td></tr></tbody></table> <hr> <a id="module_utils/audio..encodeWAV" class="group"></a> <h2 class="relative group"><a id="utilsaudioencodewavchunks-rate--blob" 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" href="#utilsaudioencodewavchunks-rate--blob"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>utils/audio~encodeWAV(chunks, rate) ⇒ Blob</span></h2> <p data-svelte-h="svelte-ukuyih">Efficiently encode audio data to a WAV file.
	WAV file specs : <a href="https://en.wikipedia.org/wiki/WAV#WAV_File_header" rel="nofollow">https://en.wikipedia.org/wiki/WAV#WAV_File_header</a></p> <p data-svelte-h="svelte-1dznmtc">Adapted from <a href="https://www.npmjs.com/package/audiobuffer-to-wav" rel="nofollow">https://www.npmjs.com/package/audiobuffer-to-wav</a></p> <p data-svelte-h="svelte-3ss2et"><strong>Kind</strong>: inner method of <a href="#module_utils/audio"><code>utils/audio</code></a><br> <strong>Returns</strong>: <code>Blob</code> - The WAV file as a Blob.</p> <table data-svelte-h="svelte-d23aeu"><thead><tr><th>Param</th><th>Type</th><th>Description</th></tr></thead> <tbody><tr><td>chunks</td><td><code>Array</code></td><td><p>The audio samples.</p></td> </tr><tr><td>rate</td><td><code>number</code></td><td><p>The sample rate.</p></td></tr></tbody></table> <hr> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers.js/blob/main/packages/transformers/docs/source/api/utils/audio.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_rvrl7f = {
	assets: "/docs/transformers.js/pr_1649/en",
	base: "/docs/transformers.js/pr_1649/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers.js/pr_1649/en/_app/immutable/entry/start.5f753a22.js"),
	import("/docs/transformers.js/pr_1649/en/_app/immutable/entry/app.db3dfcb7.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 16],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 74.7 kB
Xet hash:: 2d021a6bbcf4ead2834090bad3bf989d69f59bb9955a239d7c6c4fb26a5e9dbc

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.