Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"瞭解接口類","local":"瞭解接口類","sections":[{"title":"如何創建接口","local":"如何創建接口","sections":[],"depth":2},{"title":"一個帶音頻的簡單示例","local":"一個帶音頻的簡單示例","sections":[],"depth":2},{"title":"處理多個輸入和輸出","local":"處理多個輸入和輸出","sections":[{"title":"launch() 方法","local":"launch-方法","sections":[],"depth":3}],"depth":2},{"title":"✏️ 讓我們應用它！","local":"-讓我們應用它","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/course/pr_1021/zh-TW/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/entry/start.41617dd6.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/scheduler.37c15a92.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/singletons.75b420cf.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/index.18351ede.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/paths.241f8580.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/entry/app.89205ec4.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/index.2bf4358c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/nodes/0.72d34023.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/nodes/73.565a67bb.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/CodeBlock.4e987730.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/DocNotebookDropdown.efc1fb7c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/getInferenceSnippets.ebf8be91.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"瞭解接口類","local":"瞭解接口類","sections":[{"title":"如何創建接口","local":"如何創建接口","sections":[],"depth":2},{"title":"一個帶音頻的簡單示例","local":"一個帶音頻的簡單示例","sections":[],"depth":2},{"title":"處理多個輸入和輸出","local":"處理多個輸入和輸出","sections":[{"title":"launch() 方法","local":"launch-方法","sections":[],"depth":3}],"depth":2},{"title":"✏️ 讓我們應用它！","local":"-讓我們應用它","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="瞭解接口類" 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="#瞭解接口類"><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>瞭解接口類</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/chapter9/section3.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/chapter9/section3.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-1n241ec">在本節中，我們將仔細研究 <code>Interface</code> 類，並瞭解用於創建其的主要參數。</p> <h2 class="relative group"><a id="如何創建接口" 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="#如何創建接口"><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>如何創建接口</span></h2> <p data-svelte-h="svelte-cpncav">您會注意到 <code>Interface</code> 類有 3 個必需參數：</p> <p data-svelte-h="svelte-5xxju6"><code>Interface(fn, inputs, outputs, ...)</code></p> <p data-svelte-h="svelte-136xoue">這些參數是：</p> <ul data-svelte-h="svelte-bfg8z6"><li><code>fn</code>: 由 Gradio 接口包裝的預測函數。 該函數可以接受一個或多個參數並返回一個或多個值</li> <li><code>inputs</code>: 輸入組件類型。 Gradio 提供了許多預構建的組件，例如<code>"image"</code> 或<code>"mic"</code>。</li> <li><code>outputs</code>: 輸出組件類型。 同樣，Gradio 提供了許多預構建的組件，例如 <code>“圖像”</code>或“標籤”`。</li></ul> <p data-svelte-h="svelte-1gdrfcj">有關組件的完整列表，<a href="https://gradio.app/docs" rel="nofollow">請參閱 Gradio 文檔</a>。 每個預構建的組件都可以通過實例化該組件對應的類來定製。</p> <p data-svelte-h="svelte-wuhuoj">例如，正如我們在 <a href="/course/chapter9/2">上一節</a> 中看到的，您可以傳入一個 <code>Textbox(lines=7, label="Prompt")</code> 組件來創建一個包含 7 行和一個標籤的文本框，而不是將 <code>"textbox"</code> 傳遞給 <code>inputs</code> 參數。 | |
| 讓我們看另一個例子，這次是一個 <code>Audio</code> 組件。</p> <h2 class="relative group"><a id="一個帶音頻的簡單示例" 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="#一個帶音頻的簡單示例"><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>一個帶音頻的簡單示例</span></h2> <p data-svelte-h="svelte-1ylue7a">如前所述，Gradio 提供了許多不同的輸入和輸出。 | |
| 因此，讓我們構建一個適用於音頻的“接口”。</p> <p data-svelte-h="svelte-1qsoflg">在這個例子中，我們將構建一個音頻到音頻的函數，它需要一個音頻文件並簡單地反轉它。</p> <p data-svelte-h="svelte-1j2c7ez">我們將使用 <code>Audio</code> 組件作為輸入。 使用 <code>Audio</code> 組件時，您可以指定希望音頻的 <code>source</code> 是用戶上傳的文件還是用戶錄製聲音的麥克風。 在這種情況下，讓我們將其設置為“麥克風”。 只是為了好玩，我們會在我們的“音頻”中添加一個標籤，上面寫著“在這裡說話……”。</p> <p data-svelte-h="svelte-35cafe">此外，我們希望將音頻作為 numpy 數組接收，以便我們可以輕鬆地“反轉”它。 所以我們將 <code>"type"</code> 設置為 <code>"numpy"</code>，它會傳遞輸入data 作為 (<code>sample_rate</code>, <code>data</code>) 的元組進入我們的函數。</p> <p data-svelte-h="svelte-1498ymc">我們還將使用 <code>Audio</code> 輸出組件，它可以自動將具有采樣率和 numpy 數據數組的元組渲染為可播放的音頻文件。 在這種情況下，我們不需要進行任何自定義，因此我們將使用字符串快捷方式“audio”。</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" 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> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-keyword">import</span> gradio <span class="hljs-keyword">as</span> gr | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">reverse_audio</span>(<span class="hljs-params">audio</span>): | |
| sr, data = audio | |
| reversed_audio = (sr, np.flipud(data)) | |
| <span class="hljs-keyword">return</span> reversed_audio | |
| mic = gr.Audio(source=<span class="hljs-string">"microphone"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-string">"numpy"</span>, label=<span class="hljs-string">"Speak here..."</span>) | |
| gr.Interface(reverse_audio, mic, <span class="hljs-string">"audio"</span>).launch()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1509wnm">上面的代碼會產生一個類似下面的界面（如果你的瀏覽器沒有 | |
| 詢問您的麥克風權限， <a href="https://huggingface.co/spaces/course-demos/audio-reverse" target="_blank">open the demo in a separate tab</a>.)</p> <iframe src="https://course-demos-audio-reverse.hf.space" frameborder="0" height="250" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-2k33o5">您現在應該能夠錄製自己的聲音並聽到自己在反向說話 - 聽起來好怪👻!</p> <h2 class="relative group"><a id="處理多個輸入和輸出" 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="#處理多個輸入和輸出"><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>處理多個輸入和輸出</span></h2> <p data-svelte-h="svelte-1h3i1tv">假設我們有一個更復雜的函數，有多個輸入和輸出。在下面的示例中，我們有一個接受下拉索引、滑塊值和數字的函數，並返回一個音調的音頻樣本。</p> <p data-svelte-h="svelte-1dx3yg8">看看我們如何傳遞輸入和輸出組件列表，看看你能不能跟上正在發生的事情。</p> <p data-svelte-h="svelte-1dstpsk">這裡的關鍵是當你通過時：</p> <ul data-svelte-h="svelte-1xcyqhu"><li>輸入組件列表，每個組件依次對應一個參數。</li> <li>輸出組件列表，每個組件對應一個返回值。</li></ul> <p data-svelte-h="svelte-cp5tej">下面的代碼片段顯示了三個輸入組件如何與 <code>generate_tone()</code> 函數的三個參數對齊：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" 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> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-keyword">import</span> gradio <span class="hljs-keyword">as</span> gr | |
| notes = [<span class="hljs-string">"C"</span>, <span class="hljs-string">"C#"</span>, <span class="hljs-string">"D"</span>, <span class="hljs-string">"D#"</span>, <span class="hljs-string">"E"</span>, <span class="hljs-string">"F"</span>, <span class="hljs-string">"F#"</span>, <span class="hljs-string">"G"</span>, <span class="hljs-string">"G#"</span>, <span class="hljs-string">"A"</span>, <span class="hljs-string">"A#"</span>, <span class="hljs-string">"B"</span>] | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">generate_tone</span>(<span class="hljs-params">note, octave, duration</span>): | |
| sr = <span class="hljs-number">48000</span> | |
| a4_freq, tones_from_a4 = <span class="hljs-number">440</span>, <span class="hljs-number">12</span> * (octave - <span class="hljs-number">4</span>) + (note - <span class="hljs-number">9</span>) | |
| frequency = a4_freq * <span class="hljs-number">2</span> ** (tones_from_a4 / <span class="hljs-number">12</span>) | |
| duration = <span class="hljs-built_in">int</span>(duration) | |
| audio = np.linspace(<span class="hljs-number">0</span>, duration, duration * sr) | |
| audio = (<span class="hljs-number">20000</span> * np.sin(audio * (<span class="hljs-number">2</span> * np.pi * frequency))).astype(np.int16) | |
| <span class="hljs-keyword">return</span> (sr, audio) | |
| gr.Interface( | |
| generate_tone, | |
| [ | |
| gr.Dropdown(notes, <span class="hljs-built_in">type</span>=<span class="hljs-string">"index"</span>), | |
| gr.Slider(minimum=<span class="hljs-number">4</span>, maximum=<span class="hljs-number">6</span>, step=<span class="hljs-number">1</span>), | |
| gr.Textbox(<span class="hljs-built_in">type</span>=<span class="hljs-string">"number"</span>, value=<span class="hljs-number">1</span>, label=<span class="hljs-string">"Duration in seconds"</span>), | |
| ], | |
| <span class="hljs-string">"audio"</span>, | |
| ).launch()<!-- HTML_TAG_END --></pre></div> <iframe src="https://course-demos-generate-tone.hf.space" frameborder="0" height="450" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <h3 class="relative group"><a id="launch-方法" 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="#launch-方法"><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>launch() 方法</span></h3> <p data-svelte-h="svelte-1lc29tb">到目前為止，我們已經使用了<code>launch()</code>方法來啟動界面，但是我們 | |
| 還沒有真正討論過它的作用。</p> <p data-svelte-h="svelte-1yn25id">默認情況下，<code>launch()</code> 方法將在 Web 服務器中啟動演示正在本地運行。 如果您在 Jupyter 或 Colab 筆記本中運行代碼，那麼Gradio 會將演示 GUI 嵌入到筆記本中，以便您輕鬆使用它。</p> <p data-svelte-h="svelte-1wluu8a">您可以通過不同的參數自定義 <code>launch()</code> 的行為：</p> <ul data-svelte-h="svelte-f1qyss"><li><code>inline</code> - whether to display the interface inline on Python notebooks.</li> <li><code>inbrowser</code> - whether to automatically launch the interface in a new tab on the default browser.</li> <li><code>share</code> - whether to create a publicly shareable link from your computer for the interface. Kind of like a Google Drive link!</li></ul> <p data-svelte-h="svelte-1g3b2nk">我們將在下一節中更詳細地介紹 <code>share</code> 參數！</p> <h2 class="relative group"><a id="-讓我們應用它" 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="#-讓我們應用它"><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>✏️ 讓我們應用它！</span></h2> <p data-svelte-h="svelte-1bjo3cs">讓我們構建一個界面，讓您演示 <strong>speech-recognition</strong> 模型。 | |
| 為了讓它變得有趣，我們將接受 <em>or</em> 麥克風輸入或上傳的文件。</p> <p data-svelte-h="svelte-1uahifx">像往常一樣，我們將使用 🤗 Transformers 中的 <code>pipeline()</code> 函數加載我們的語音識別模型。如果您需要快速複習，您可以返回 <a href="/course/chapter1/3">第 1 章中的那個部分</a>。 接下來，我們將實現一個 <code>transcribe_audio()</code> 函數來處理音頻並返回轉錄。 最後，我們將把這個函數包裝在一個 <code>Interface</code> 中，其中 <code>Audio</code> 組件用於輸入，只有文本用於輸出。 總而言之，此應用程序的代碼如下：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" 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> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline | |
| <span class="hljs-keyword">import</span> gradio <span class="hljs-keyword">as</span> gr | |
| model = pipeline(<span class="hljs-string">"automatic-speech-recognition"</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">transcribe_audio</span>(<span class="hljs-params">mic=<span class="hljs-literal">None</span>, file=<span class="hljs-literal">None</span></span>): | |
| <span class="hljs-keyword">if</span> mic <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span>: | |
| audio = mic | |
| <span class="hljs-keyword">elif</span> file <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span>: | |
| audio = file | |
| <span class="hljs-keyword">else</span>: | |
| <span class="hljs-keyword">return</span> <span class="hljs-string">"You must either provide a mic recording or a file"</span> | |
| transcription = model(audio)[<span class="hljs-string">"text"</span>] | |
| <span class="hljs-keyword">return</span> transcription | |
| gr.Interface( | |
| fn=transcribe_audio, | |
| inputs=[ | |
| gr.Audio(source=<span class="hljs-string">"microphone"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-string">"filepath"</span>, optional=<span class="hljs-literal">True</span>), | |
| gr.Audio(source=<span class="hljs-string">"upload"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-string">"filepath"</span>, optional=<span class="hljs-literal">True</span>), | |
| ], | |
| outputs=<span class="hljs-string">"text"</span>, | |
| ).launch()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1e8u067">如果您的瀏覽器沒有要求您提供麥克風權限，<a href="https://huggingface.co/spaces/course-demos/audio-reverse" target="_blank">open the demo in a separate tab</a>.</p> <iframe src="https://course-demos-asr.hf.space" frameborder="0" height="550" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-bcbhfh">就是這樣！ 您現在可以使用此界面來轉錄音頻。 注意這裡 | |
| 通過將 <code>optional</code> 參數作為 <code>True</code> 傳遞，我們允許用戶 | |
| 提供麥克風或音頻文件（或兩者都不提供，但這會返回錯誤消息）。</p> <p data-svelte-h="svelte-erzn5k">繼續看看如何與他人分享您的界面！</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/zh-TW/chapter9/3.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_kgz26w = { | |
| assets: "/docs/course/pr_1021/zh-TW", | |
| base: "/docs/course/pr_1021/zh-TW", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/course/pr_1021/zh-TW/_app/immutable/entry/start.41617dd6.js"), | |
| import("/docs/course/pr_1021/zh-TW/_app/immutable/entry/app.89205ec4.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 73], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 28.4 kB
- Xet hash:
- 2bc69a2652b00739e6aca5c0877e8b6e4e53746cb1b73e5c400a0956bc608315
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.