course/pr_1213/es/_app/immutable/nodes/7.304573ca.js

import{s as Sl,a as Rl,o as ql}from"../chunks/scheduler.505acc25.js";import{S as Ql,i as El,e as M,s as n,c as i,h as Yl,a as y,d as l,b as a,f as Nl,g as p,j as d,k as f,l as Fl,m as t,n as r,t as o,o as m,p as c}from"../chunks/index.e22abd30.js";import{C as Xl,H as u,E as Ll}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.a144e953.js";import{Y as _l}from"../chunks/Youtube.7545e4b1.js";import{C as J}from"../chunks/CodeBlock.f6688f67.js";import{C as Pl}from"../chunks/CourseFloatingBanner.f0a2dc21.js";import{F as Dl}from"../chunks/FrameworkSwitchCourse.c2af54e8.js";function Ol(ml){let j,Se,T,Re,g,Qe,x,Ee,C,Ye,I,Fe,B,cl="En esta sección veremos qué pueden hacer los modelos Transformer y usaremos nuestra primera herramienta de la librería 🤗 Transformers: la función <code>pipeline()</code>.",Xe,$,Ml='<p>Mira el botón <em>Open in Colab</em> de la esquina superior derecha. Haz clic para abrir un notebook de Google Colab con todos los ejemplos de código de esta sección.</p> <p>Si quieres ejecutar los ejemplos de forma local, te recomendamos revisar la <a href="/course/chapter0">instalación</a>.</p>',Le,v,_e,G,yl="Los modelos Transformer se usan para resolver todo tipo de tareas en distintas modalidades, entre ellas procesamiento de lenguaje natural, visión por computador, audio y más. Estas son algunas de las empresas y organizaciones que usan Hugging Face y modelos Transformer, y que además contribuyen a la comunidad compartiendo sus modelos:",Pe,w,dl,De,Z,ul='La librería <a href="https://github.com/huggingface/transformers" rel="nofollow">🤗 Transformers</a> ofrece la funcionalidad necesaria para crear y usar esos modelos compartidos. El <a href="https://huggingface.co/models" rel="nofollow">Model Hub</a> contiene millones de modelos preentrenados que cualquiera puede descargar y utilizar. También puedes subir tus propios modelos al Hub.',Oe,h,Jl='<p>⚠️ El Hugging Face Hub no se limita a modelos Transformer. Cualquiera puede compartir el tipo de modelos o datasets que quiera. <a href="https://huggingface.co/join">Crea una cuenta en huggingface.co</a> para aprovechar todas las funciones disponibles.</p>',Ke,W,jl="Antes de profundizar en cómo funcionan internamente los modelos Transformer, veamos algunos ejemplos de cómo se pueden usar para resolver problemas interesantes de PLN.",es,k,ss,H,ls,V,fl="El objeto más básico de la librería 🤗 Transformers es la función <code>pipeline()</code>. Conecta un modelo con sus pasos necesarios de preprocesamiento y posprocesamiento, de forma que podamos introducir texto directamente y obtener una respuesta comprensible:",ts,A,ns,z,as,N,Tl="Incluso podemos pasar varias oraciones:",is,S,ps,R,rs,q,gl="Por defecto, este pipeline selecciona un modelo preentrenado concreto que se ha ajustado para análisis de sentimiento en inglés. El modelo se descarga y se almacena en caché cuando creas el objeto <code>classifier</code>.",os,Q,$l="Hay tres pasos principales cuando pasas texto a un pipeline:",ms,E,wl="<li>El texto se preprocesa en un formato que el modelo pueda entender.</li> <li>Las entradas preprocesadas se pasan al modelo.</li> <li>Las predicciones del modelo se posprocesan para que tengan sentido para ti.</li>",cs,Y,Ms,F,hl="La función <code>pipeline()</code> soporta múltiples modalidades, así que puedes trabajar con texto, imágenes, audio e incluso tareas multimodales. En este curso nos centraremos en tareas de texto, pero conviene entender el potencial de la arquitectura Transformer.",ys,U,Ul='<p>Para ver una lista completa y actualizada de pipelines, consulta la <a href="https://huggingface.co/docs/hub/en/models-tasks" rel="nofollow">documentación de 🤗 Transformers</a>.</p>',ds,X,us,L,bl="<li><code>text-generation</code>: genera texto a partir de un prompt.</li> <li><code>text-classification</code>: clasifica texto en categorías predefinidas.</li> <li><code>summarization</code>: crea una versión más corta de un texto conservando la información clave.</li> <li><code>translation</code>: traduce texto de un idioma a otro.</li> <li><code>zero-shot-classification</code>: clasifica texto sin entrenamiento previo sobre etiquetas concretas.</li> <li><code>feature-extraction</code>: extrae representaciones vectoriales del texto.</li>",Js,_,js,P,xl="<li><code>image-to-text</code>: genera descripciones de texto a partir de imágenes.</li> <li><code>image-classification</code>: identifica objetos en una imagen.</li> <li><code>object-detection</code>: localiza e identifica objetos en imágenes.</li>",fs,D,Ts,O,Cl="<li><code>automatic-speech-recognition</code>: convierte voz en texto.</li> <li><code>audio-classification</code>: clasifica audio en categorías.</li> <li><code>text-to-speech</code>: convierte texto en audio hablado.</li>",gs,K,$s,ee,Il="<li><code>image-text-to-text</code>: responde a una imagen a partir de un prompt de texto.</li>",ws,se,Bl="Veamos algunos de estos pipelines con más detalle.",hs,le,Us,te,vl="Empezaremos con una tarea más exigente: clasificar textos que no están etiquetados. Para este caso, el pipeline <code>zero-shot-classification</code> es muy potente: te permite especificar qué etiquetas usar, así que no dependes de las etiquetas del modelo preentrenado.",bs,ne,xs,ae,Cs,b,Gl="<p>✏️ <strong>Pruébalo</strong>. Juega con tus propias secuencias y etiquetas y observa cómo se comporta el modelo.</p>",Is,ie,Bs,pe,vs,re,Gs,oe,Zl="Puedes controlar cuántas secuencias distintas se generan con <code>num_return_sequences</code> y la longitud total del texto de salida con <code>max_length</code>.",Zs,me,Ws,ce,Wl='Probemos el modelo <a href="https://huggingface.co/HuggingFaceTB/SmolLM2-360M" rel="nofollow"><code>HuggingFaceTB/SmolLM2-360M</code></a>:',ks,Me,Hs,ye,Vs,de,As,ue,kl='Todos los modelos pueden probarse directamente en el navegador usando Inference Providers, disponibles en el <a href="https://huggingface.co/docs/inference-providers/en/index" rel="nofollow">sitio web</a>.',zs,Je,Ns,je,Ss,fe,Rs,Te,qs,ge,Qs,$e,Es,we,Ys,he,Fs,Ue,Xs,be,Ls,xe,Hl="El resumen automático consiste en reducir un texto a una versión más corta conservando la información importante.",_s,Ce,Ps,Ie,Ds,Be,Os,ve,Ks,Ge,el,Ze,sl,We,ll,ke,tl,He,nl,Ve,Vl="Una aplicación potente de los modelos Transformer es su capacidad para combinar y procesar datos procedentes de múltiples fuentes.",al,Ae,il,ze,Al="Los pipelines mostrados en este capítulo son sobre todo demostrativos. En el próximo capítulo aprenderás qué hay dentro de una función <code>pipeline()</code> y cómo personalizar su comportamiento.",pl,Ne,rl,qe,ol;return g=new Dl({props:{fw:ml[0]}}),x=new Xl({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),C=new u({props:{title:"Transformers, ¿qué pueden hacer?",local:"transformers-what-can-they-do",headingTag:"h1"}}),I=new Pl({props:{chapter:1,classNames:"absolute z-10 right-0 top-0",notebooks:[{label:"Google Colab",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/en/chapter1/section3.ipynb"},{label:"Aws Studio",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/en/chapter1/section3.ipynb"}]}}),v=new u({props:{title:"Los Transformers están en todas partes",local:"transformers-are-everywhere",headingTag:"h2"}}),k=new u({props:{title:"Trabajar con pipelines",local:"working-with-pipelines",headingTag:"h2"}}),H=new _l({props:{id:"tiZFewofSLM"}}),A=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBY2xhc3NpZmllciUyMCUzRCUyMHBpcGVsaW5lKCUyMnNlbnRpbWVudC1hbmFseXNpcyUyMiklMEFjbGFzc2lmaWVyKCUyMkkndmUlMjBiZWVuJTIwd2FpdGluZyUyMGZvciUyMGElMjBIdWdnaW5nRmFjZSUyMGNvdXJzZSUyMG15JTIwd2hvbGUlMjBsaWZlLiUyMik=",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

classifier = pipeline(<span class="hljs-string">&quot;sentiment-analysis&quot;</span>)
classifier(<span class="hljs-string">&quot;I&#x27;ve been waiting for a HuggingFace course my whole life.&quot;</span>)`,wrap:!1}}),z=new J({props:{code:"JTVCJTdCJ2xhYmVsJyUzQSUyMCdQT1NJVElWRSclMkMlMjAnc2NvcmUnJTNBJTIwMC45NTk4MDQ3MTM3MjYwNDM3JTdEJTVE",highlighted:'[{<span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;POSITIVE&#x27;</span>, <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.9598047137260437</span>}]',wrap:!1}}),S=new J({props:{code:"Y2xhc3NpZmllciglMEElMjAlMjAlMjAlMjAlNUIlMjJJJ3ZlJTIwYmVlbiUyMHdhaXRpbmclMjBmb3IlMjBhJTIwSHVnZ2luZ0ZhY2UlMjBjb3Vyc2UlMjBteSUyMHdob2xlJTIwbGlmZS4lMjIlMkMlMjAlMjJJJTIwaGF0ZSUyMHRoaXMlMjBzbyUyMG11Y2ghJTIyJTVEJTBBKQ==",highlighted:`classifier(
    [<span class="hljs-string">&quot;I&#x27;ve been waiting for a HuggingFace course my whole life.&quot;</span>, <span class="hljs-string">&quot;I hate this so much!&quot;</span>]
)`,wrap:!1}}),R=new J({props:{code:"JTVCJTdCJ2xhYmVsJyUzQSUyMCdQT1NJVElWRSclMkMlMjAnc2NvcmUnJTNBJTIwMC45NTk4MDQ3MTM3MjYwNDM3JTdEJTJDJTBBJTIwJTdCJ2xhYmVsJyUzQSUyMCdORUdBVElWRSclMkMlMjAnc2NvcmUnJTNBJTIwMC45OTk0NTU4MDk1OTMyMDA3JTdEJTVE",highlighted:`[{<span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;POSITIVE&#x27;</span>, <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.9598047137260437</span>},
 {<span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;NEGATIVE&#x27;</span>, <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.9994558095932007</span>}]`,wrap:!1}}),Y=new u({props:{title:"Pipelines disponibles para distintas modalidades",local:"pipelines-disponibles-para-distintas-modalidades",headingTag:"h2"}}),X=new u({props:{title:"Pipelines de texto",local:"pipelines-de-texto",headingTag:"h3"}}),_=new u({props:{title:"Pipelines de imagen",local:"pipelines-de-imagen",headingTag:"h3"}}),D=new u({props:{title:"Pipelines de audio",local:"pipelines-de-audio",headingTag:"h3"}}),K=new u({props:{title:"Pipelines multimodales",local:"pipelines-multimodales",headingTag:"h3"}}),le=new u({props:{title:"Clasificación zero-shot",local:"zero-shot-classification",headingTag:"h2"}}),ne=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBY2xhc3NpZmllciUyMCUzRCUyMHBpcGVsaW5lKCUyMnplcm8tc2hvdC1jbGFzc2lmaWNhdGlvbiUyMiklMEFjbGFzc2lmaWVyKCUwQSUyMCUyMCUyMCUyMCUyMlRoaXMlMjBpcyUyMGElMjBjb3Vyc2UlMjBhYm91dCUyMHRoZSUyMFRyYW5zZm9ybWVycyUyMGxpYnJhcnklMjIlMkMlMEElMjAlMjAlMjAlMjBjYW5kaWRhdGVfbGFiZWxzJTNEJTVCJTIyZWR1Y2F0aW9uJTIyJTJDJTIwJTIycG9saXRpY3MlMjIlMkMlMjAlMjJidXNpbmVzcyUyMiU1RCUyQyUwQSk=",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

classifier = pipeline(<span class="hljs-string">&quot;zero-shot-classification&quot;</span>)
classifier(
    <span class="hljs-string">&quot;This is a course about the Transformers library&quot;</span>,
    candidate_labels=[<span class="hljs-string">&quot;education&quot;</span>, <span class="hljs-string">&quot;politics&quot;</span>, <span class="hljs-string">&quot;business&quot;</span>],
)`,wrap:!1}}),ae=new J({props:{code:"JTdCJ3NlcXVlbmNlJyUzQSUyMCdUaGlzJTIwaXMlMjBhJTIwY291cnNlJTIwYWJvdXQlMjB0aGUlMjBUcmFuc2Zvcm1lcnMlMjBsaWJyYXJ5JyUyQyUwQSUyMCdsYWJlbHMnJTNBJTIwJTVCJ2VkdWNhdGlvbiclMkMlMjAnYnVzaW5lc3MnJTJDJTIwJ3BvbGl0aWNzJyU1RCUyQyUwQSUyMCdzY29yZXMnJTNBJTIwJTVCMC44NDQ1OTYzODU5NTU4MTA1JTJDJTIwMC4xMTE5NzYyNTg0NTY3MDclMkMlMjAwLjA0MzQyNzQ0ODcxOTczOTkxNCU1RCU3RA==",highlighted:`{<span class="hljs-string">&#x27;sequence&#x27;</span>: <span class="hljs-string">&#x27;This is a course about the Transformers library&#x27;</span>,
 <span class="hljs-string">&#x27;labels&#x27;</span>: [<span class="hljs-string">&#x27;education&#x27;</span>, <span class="hljs-string">&#x27;business&#x27;</span>, <span class="hljs-string">&#x27;politics&#x27;</span>],
 <span class="hljs-string">&#x27;scores&#x27;</span>: [<span class="hljs-number">0.8445963859558105</span>, <span class="hljs-number">0.111976258456707</span>, <span class="hljs-number">0.043427448719739914</span>]}`,wrap:!1}}),ie=new u({props:{title:"Generación de texto",local:"text-generation",headingTag:"h2"}}),pe=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBZ2VuZXJhdG9yJTIwJTNEJTIwcGlwZWxpbmUoJTIydGV4dC1nZW5lcmF0aW9uJTIyKSUwQWdlbmVyYXRvciglMjJJbiUyMHRoaXMlMjBjb3Vyc2UlMkMlMjB3ZSUyMHdpbGwlMjB0ZWFjaCUyMHlvdSUyMGhvdyUyMHRvJTIyKQ==",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

generator = pipeline(<span class="hljs-string">&quot;text-generation&quot;</span>)
generator(<span class="hljs-string">&quot;In this course, we will teach you how to&quot;</span>)`,wrap:!1}}),re=new J({props:{code:"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",highlighted:`[{<span class="hljs-string">&#x27;generated_text&#x27;</span>: <span class="hljs-string">&#x27;In this course, we will teach you how to understand and use &#x27;</span>
                    <span class="hljs-string">&#x27;data flow and data interchange when handling user data. We &#x27;</span>
                    <span class="hljs-string">&#x27;will be working with one or more of the most commonly used &#x27;</span>
                    <span class="hljs-string">&#x27;data flows — data flows of various types, as seen by the &#x27;</span>
                    <span class="hljs-string">&#x27;HTTP&#x27;</span>}]`,wrap:!1}}),me=new u({props:{title:"Usar cualquier modelo del Hub en un pipeline",local:"using-any-model-from-the-hub-in-a-pipeline",headingTag:"h2"}}),Me=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBZ2VuZXJhdG9yJTIwJTNEJTIwcGlwZWxpbmUoJTIydGV4dC1nZW5lcmF0aW9uJTIyJTJDJTIwbW9kZWwlM0QlMjJIdWdnaW5nRmFjZVRCJTJGU21vbExNMi0zNjBNJTIyKSUwQWdlbmVyYXRvciglMEElMjAlMjAlMjAlMjAlMjJJbiUyMHRoaXMlMjBjb3Vyc2UlMkMlMjB3ZSUyMHdpbGwlMjB0ZWFjaCUyMHlvdSUyMGhvdyUyMHRvJTIyJTJDJTBBJTIwJTIwJTIwJTIwbWF4X2xlbmd0aCUzRDMwJTJDJTBBJTIwJTIwJTIwJTIwbnVtX3JldHVybl9zZXF1ZW5jZXMlM0QyJTJDJTBBKQ==",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

generator = pipeline(<span class="hljs-string">&quot;text-generation&quot;</span>, model=<span class="hljs-string">&quot;HuggingFaceTB/SmolLM2-360M&quot;</span>)
generator(
    <span class="hljs-string">&quot;In this course, we will teach you how to&quot;</span>,
    max_length=<span class="hljs-number">30</span>,
    num_return_sequences=<span class="hljs-number">2</span>,
)`,wrap:!1}}),ye=new J({props:{code:"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",highlighted:`[{<span class="hljs-string">&#x27;generated_text&#x27;</span>: <span class="hljs-string">&#x27;In this course, we will teach you how to manipulate the world and &#x27;</span>
                    <span class="hljs-string">&#x27;move your mental and physical capabilities to your advantage.&#x27;</span>},
 {<span class="hljs-string">&#x27;generated_text&#x27;</span>: <span class="hljs-string">&#x27;In this course, we will teach you how to become an expert and &#x27;</span>
                    <span class="hljs-string">&#x27;practice realtime, and with a hands on experience on both real &#x27;</span>
                    <span class="hljs-string">&#x27;time and real&#x27;</span>}]`,wrap:!1}}),de=new u({props:{title:"Inference Providers",local:"inference-providers",headingTag:"h3"}}),Je=new u({props:{title:"Rellenado de máscaras",local:"mask-filling",headingTag:"h2"}}),je=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBdW5tYXNrZXIlMjAlM0QlMjBwaXBlbGluZSglMjJmaWxsLW1hc2slMjIpJTBBdW5tYXNrZXIoJTIyVGhpcyUyMGNvdXJzZSUyMHdpbGwlMjB0ZWFjaCUyMHlvdSUyMGFsbCUyMGFib3V0JTIwJTNDbWFzayUzRSUyMG1vZGVscy4lMjIlMkMlMjB0b3BfayUzRDIp",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

unmasker = pipeline(<span class="hljs-string">&quot;fill-mask&quot;</span>)
unmasker(<span class="hljs-string">&quot;This course will teach you all about &lt;mask&gt; models.&quot;</span>, top_k=<span class="hljs-number">2</span>)`,wrap:!1}}),fe=new J({props:{code:"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",highlighted:`[{<span class="hljs-string">&#x27;sequence&#x27;</span>: <span class="hljs-string">&#x27;This course will teach you all about mathematical models.&#x27;</span>,
  <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.19619831442832947</span>,
  <span class="hljs-string">&#x27;token&#x27;</span>: <span class="hljs-number">30412</span>,
  <span class="hljs-string">&#x27;token_str&#x27;</span>: <span class="hljs-string">&#x27; mathematical&#x27;</span>},
 {<span class="hljs-string">&#x27;sequence&#x27;</span>: <span class="hljs-string">&#x27;This course will teach you all about computational models.&#x27;</span>,
  <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.04052725434303284</span>,
  <span class="hljs-string">&#x27;token&#x27;</span>: <span class="hljs-number">38163</span>,
  <span class="hljs-string">&#x27;token_str&#x27;</span>: <span class="hljs-string">&#x27; computational&#x27;</span>}]`,wrap:!1}}),Te=new u({props:{title:"Reconocimiento de entidades nombradas",local:"named-entity-recognition",headingTag:"h2"}}),ge=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBbmVyJTIwJTNEJTIwcGlwZWxpbmUoJTIybmVyJTIyJTJDJTIwZ3JvdXBlZF9lbnRpdGllcyUzRFRydWUpJTBBbmVyKCUyMk15JTIwbmFtZSUyMGlzJTIwU3lsdmFpbiUyMGFuZCUyMEklMjB3b3JrJTIwYXQlMjBIdWdnaW5nJTIwRmFjZSUyMGluJTIwQnJvb2tseW4uJTIyKQ==",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

ner = pipeline(<span class="hljs-string">&quot;ner&quot;</span>, grouped_entities=<span class="hljs-literal">True</span>)
ner(<span class="hljs-string">&quot;My name is Sylvain and I work at Hugging Face in Brooklyn.&quot;</span>)`,wrap:!1}}),$e=new J({props:{code:"JTVCJTdCJ2VudGl0eV9ncm91cCclM0ElMjAnUEVSJyUyQyUyMCdzY29yZSclM0ElMjAwLjk5ODE2JTJDJTIwJ3dvcmQnJTNBJTIwJ1N5bHZhaW4nJTJDJTIwJ3N0YXJ0JyUzQSUyMDExJTJDJTIwJ2VuZCclM0ElMjAxOCU3RCUyQyUyMCUwQSUyMCU3QidlbnRpdHlfZ3JvdXAnJTNBJTIwJ09SRyclMkMlMjAnc2NvcmUnJTNBJTIwMC45Nzk2MCUyQyUyMCd3b3JkJyUzQSUyMCdIdWdnaW5nJTIwRmFjZSclMkMlMjAnc3RhcnQnJTNBJTIwMzMlMkMlMjAnZW5kJyUzQSUyMDQ1JTdEJTJDJTIwJTBBJTIwJTdCJ2VudGl0eV9ncm91cCclM0ElMjAnTE9DJyUyQyUyMCdzY29yZSclM0ElMjAwLjk5MzIxJTJDJTIwJ3dvcmQnJTNBJTIwJ0Jyb29rbHluJyUyQyUyMCdzdGFydCclM0ElMjA0OSUyQyUyMCdlbmQnJTNBJTIwNTclN0QlMEElNUQ=",highlighted:`[{<span class="hljs-string">&#x27;entity_group&#x27;</span>: <span class="hljs-string">&#x27;PER&#x27;</span>, <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.99816</span>, <span class="hljs-string">&#x27;word&#x27;</span>: <span class="hljs-string">&#x27;Sylvain&#x27;</span>, <span class="hljs-string">&#x27;start&#x27;</span>: <span class="hljs-number">11</span>, <span class="hljs-string">&#x27;end&#x27;</span>: <span class="hljs-number">18</span>}, 
 {<span class="hljs-string">&#x27;entity_group&#x27;</span>: <span class="hljs-string">&#x27;ORG&#x27;</span>, <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.97960</span>, <span class="hljs-string">&#x27;word&#x27;</span>: <span class="hljs-string">&#x27;Hugging Face&#x27;</span>, <span class="hljs-string">&#x27;start&#x27;</span>: <span class="hljs-number">33</span>, <span class="hljs-string">&#x27;end&#x27;</span>: <span class="hljs-number">45</span>}, 
 {<span class="hljs-string">&#x27;entity_group&#x27;</span>: <span class="hljs-string">&#x27;LOC&#x27;</span>, <span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.99321</span>, <span class="hljs-string">&#x27;word&#x27;</span>: <span class="hljs-string">&#x27;Brooklyn&#x27;</span>, <span class="hljs-string">&#x27;start&#x27;</span>: <span class="hljs-number">49</span>, <span class="hljs-string">&#x27;end&#x27;</span>: <span class="hljs-number">57</span>}
]`,wrap:!1}}),we=new u({props:{title:"Question answering",local:"question-answering",headingTag:"h2"}}),he=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBcXVlc3Rpb25fYW5zd2VyZXIlMjAlM0QlMjBwaXBlbGluZSglMjJxdWVzdGlvbi1hbnN3ZXJpbmclMjIpJTBBcXVlc3Rpb25fYW5zd2VyZXIoJTBBJTIwJTIwJTIwJTIwcXVlc3Rpb24lM0QlMjJXaGVyZSUyMGRvJTIwSSUyMHdvcmslM0YlMjIlMkMlMEElMjAlMjAlMjAlMjBjb250ZXh0JTNEJTIyTXklMjBuYW1lJTIwaXMlMjBTeWx2YWluJTIwYW5kJTIwSSUyMHdvcmslMjBhdCUyMEh1Z2dpbmclMjBGYWNlJTIwaW4lMjBCcm9va2x5biUyMiUyQyUwQSk=",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

question_answerer = pipeline(<span class="hljs-string">&quot;question-answering&quot;</span>)
question_answerer(
    question=<span class="hljs-string">&quot;Where do I work?&quot;</span>,
    context=<span class="hljs-string">&quot;My name is Sylvain and I work at Hugging Face in Brooklyn&quot;</span>,
)`,wrap:!1}}),Ue=new J({props:{code:"JTdCJ3Njb3JlJyUzQSUyMDAuNjM4NTkxNjQ3MTQ4MTMyMyUyQyUyMCdzdGFydCclM0ElMjAzMyUyQyUyMCdlbmQnJTNBJTIwNDUlMkMlMjAnYW5zd2VyJyUzQSUyMCdIdWdnaW5nJTIwRmFjZSclN0Q=",highlighted:'{<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.6385916471481323</span>, <span class="hljs-string">&#x27;start&#x27;</span>: <span class="hljs-number">33</span>, <span class="hljs-string">&#x27;end&#x27;</span>: <span class="hljs-number">45</span>, <span class="hljs-string">&#x27;answer&#x27;</span>: <span class="hljs-string">&#x27;Hugging Face&#x27;</span>}',wrap:!1}}),be=new u({props:{title:"Resumen automático",local:"summarization",headingTag:"h2"}}),Ce=new u({props:{title:"Traducción",local:"translation",headingTag:"h2"}}),Ie=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBdHJhbnNsYXRvciUyMCUzRCUyMHBpcGVsaW5lKCUyMnRyYW5zbGF0aW9uJTIyJTJDJTIwbW9kZWwlM0QlMjJIZWxzaW5raS1OTFAlMkZvcHVzLW10LWZyLWVuJTIyKSUwQXRyYW5zbGF0b3IoJTIyQ2UlMjBjb3VycyUyMGVzdCUyMHByb2R1aXQlMjBwYXIlMjBIdWdnaW5nJTIwRmFjZS4lMjIp",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

translator = pipeline(<span class="hljs-string">&quot;translation&quot;</span>, model=<span class="hljs-string">&quot;Helsinki-NLP/opus-mt-fr-en&quot;</span>)
translator(<span class="hljs-string">&quot;Ce cours est produit par Hugging Face.&quot;</span>)`,wrap:!1}}),Be=new J({props:{code:"JTVCJTdCJ3RyYW5zbGF0aW9uX3RleHQnJTNBJTIwJ1RoaXMlMjBjb3Vyc2UlMjBpcyUyMHByb2R1Y2VkJTIwYnklMjBIdWdnaW5nJTIwRmFjZS4nJTdEJTVE",highlighted:'[{<span class="hljs-string">&#x27;translation_text&#x27;</span>: <span class="hljs-string">&#x27;This course is produced by Hugging Face.&#x27;</span>}]',wrap:!1}}),ve=new u({props:{title:"Pipelines de imagen y audio",local:"pipelines-de-imagen-y-audio",headingTag:"h2"}}),Ge=new u({props:{title:"Clasificación de imágenes",local:"clasificación-de-imágenes",headingTag:"h3"}}),Ze=new J({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

image_classifier = pipeline(
    task=<span class="hljs-string">&quot;image-classification&quot;</span>, model=<span class="hljs-string">&quot;google/vit-base-patch16-224&quot;</span>
)
result = image_classifier(
    <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg&quot;</span>
)
<span class="hljs-built_in">print</span>(result)`,wrap:!1}}),We=new u({props:{title:"Reconocimiento automático de voz",local:"reconocimiento-automático-de-voz",headingTag:"h3"}}),ke=new J({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBdHJhbnNjcmliZXIlMjAlM0QlMjBwaXBlbGluZSglMEElMjAlMjAlMjAlMjB0YXNrJTNEJTIyYXV0b21hdGljLXNwZWVjaC1yZWNvZ25pdGlvbiUyMiUyQyUyMG1vZGVsJTNEJTIyb3BlbmFpJTJGd2hpc3Blci1sYXJnZS12MyUyMiUwQSklMEFyZXN1bHQlMjAlM0QlMjB0cmFuc2NyaWJlciglMEElMjAlMjAlMjAlMjAlMjJodHRwcyUzQSUyRiUyRmh1Z2dpbmdmYWNlLmNvJTJGZGF0YXNldHMlMkZOYXJzaWwlMkZhc3JfZHVtbXklMkZyZXNvbHZlJTJGbWFpbiUyRm1say5mbGFjJTIyJTBBKSUwQXByaW50KHJlc3VsdCk=",highlighted:`<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

transcriber = pipeline(
    task=<span class="hljs-string">&quot;automatic-speech-recognition&quot;</span>, model=<span class="hljs-string">&quot;openai/whisper-large-v3&quot;</span>
)
result = transcriber(
    <span class="hljs-string">&quot;https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac&quot;</span>
)
<span class="hljs-built_in">print</span>(result)`,wrap:!1}}),He=new u({props:{title:"Combinar datos de múltiples fuentes",local:"combinar-datos-de-múltiples-fuentes",headingTag:"h2"}}),Ae=new u({props:{title:"Conclusión",local:"conclusión",headingTag:"h2"}}),Ne=new Ll({props:{source:"https://github.com/huggingface/course/blob/main/chapters/es/chapter1/3.mdx"}}),{c(){j=M("meta"),Se=n(),T=M("p"),Re=n(),i(g.$$.fragment),Qe=n(),i(x.$$.fragment),Ee=n(),i(C.$$.fragment),Ye=n(),i(I.$$.fragment),Fe=n(),B=M("p"),B.innerHTML=cl,Xe=n(),$=M("blockquote"),$.innerHTML=Ml,Le=n(),i(v.$$.fragment),_e=n(),G=M("p"),G.textContent=yl,Pe=n(),w=M("img"),De=n(),Z=M("p"),Z.innerHTML=ul,Oe=n(),h=M("blockquote"),h.innerHTML=Jl,Ke=n(),W=M("p"),W.textContent=jl,es=n(),i(k.$$.fragment),ss=n(),i(H.$$.fragment),ls=n(),V=M("p"),V.innerHTML=fl,ts=n(),i(A.$$.fragment),ns=n(),i(z.$$.fragment),as=n(),N=M("p"),N.textContent=Tl,is=n(),i(S.$$.fragment),ps=n(),i(R.$$.fragment),rs=n(),q=M("p"),q.innerHTML=gl,os=n(),Q=M("p"),Q.textContent=$l,ms=n(),E=M("ol"),E.innerHTML=wl,cs=n(),i(Y.$$.fragment),Ms=n(),F=M("p"),F.innerHTML=hl,ys=n(),U=M("blockquote"),U.innerHTML=Ul,ds=n(),i(X.$$.fragment),us=n(),L=M("ul"),L.innerHTML=bl,Js=n(),i(_.$$.fragment),js=n(),P=M("ul"),P.innerHTML=xl,fs=n(),i(D.$$.fragment),Ts=n(),O=M("ul"),O.innerHTML=Cl,gs=n(),i(K.$$.fragment),$s=n(),ee=M("ul"),ee.innerHTML=Il,ws=n(),se=M("p"),se.textContent=Bl,hs=n(),i(le.$$.fragment),Us=n(),te=M("p"),te.innerHTML=vl,bs=n(),i(ne.$$.fragment),xs=n(),i(ae.$$.fragment),Cs=n(),b=M("blockquote"),b.innerHTML=Gl,Is=n(),i(ie.$$.fragment),Bs=n(),i(pe.$$.fragment),vs=n(),i(re.$$.fragment),Gs=n(),oe=M("p"),oe.innerHTML=Zl,Zs=n(),i(me.$$.fragment),Ws=n(),ce=M("p"),ce.innerHTML=Wl,ks=n(),i(Me.$$.fragment),Hs=n(),i(ye.$$.fragment),Vs=n(),i(de.$$.fragment),As=n(),ue=M("p"),ue.innerHTML=kl,zs=n(),i(Je.$$.fragment),Ns=n(),i(je.$$.fragment),Ss=n(),i(fe.$$.fragment),Rs=n(),i(Te.$$.fragment),qs=n(),i(ge.$$.fragment),Qs=n(),i($e.$$.fragment),Es=n(),i(we.$$.fragment),Ys=n(),i(he.$$.fragment),Fs=n(),i(Ue.$$.fragment),Xs=n(),i(be.$$.fragment),Ls=n(),xe=M("p"),xe.textContent=Hl,_s=n(),i(Ce.$$.fragment),Ps=n(),i(Ie.$$.fragment),Ds=n(),i(Be.$$.fragment),Os=n(),i(ve.$$.fragment),Ks=n(),i(Ge.$$.fragment),el=n(),i(Ze.$$.fragment),sl=n(),i(We.$$.fragment),ll=n(),i(ke.$$.fragment),tl=n(),i(He.$$.fragment),nl=n(),Ve=M("p"),Ve.textContent=Vl,al=n(),i(Ae.$$.fragment),il=n(),ze=M("p"),ze.innerHTML=Al,pl=n(),i(Ne.$$.fragment),rl=n(),qe=M("p"),this.h()},l(e){const s=Yl("svelte-u9bgzb",document.head);j=y(s,"META",{name:!0,content:!0}),s.forEach(l),Se=a(e),T=y(e,"P",{}),Nl(T).forEach(l),Re=a(e),p(g.$$.fragment,e),Qe=a(e),p(x.$$.fragment,e),Ee=a(e),p(C.$$.fragment,e),Ye=a(e),p(I.$$.fragment,e),Fe=a(e),B=y(e,"P",{"data-svelte-h":!0}),d(B)!=="svelte-kg3244"&&(B.innerHTML=cl),Xe=a(e),$=y(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),d($)!=="svelte-16wy2p"&&($.innerHTML=Ml),Le=a(e),p(v.$$.fragment,e),_e=a(e),G=y(e,"P",{"data-svelte-h":!0}),d(G)!=="svelte-6hp81r"&&(G.textContent=yl),Pe=a(e),w=y(e,"IMG",{src:!0,alt:!0,width:!0}),De=a(e),Z=y(e,"P",{"data-svelte-h":!0}),d(Z)!=="svelte-17waus1"&&(Z.innerHTML=ul),Oe=a(e),h=y(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),d(h)!=="svelte-wafpyk"&&(h.innerHTML=Jl),Ke=a(e),W=y(e,"P",{"data-svelte-h":!0}),d(W)!=="svelte-3kxpyr"&&(W.textContent=jl),es=a(e),p(k.$$.fragment,e),ss=a(e),p(H.$$.fragment,e),ls=a(e),V=y(e,"P",{"data-svelte-h":!0}),d(V)!=="svelte-ly6zm3"&&(V.innerHTML=fl),ts=a(e),p(A.$$.fragment,e),ns=a(e),p(z.$$.fragment,e),as=a(e),N=y(e,"P",{"data-svelte-h":!0}),d(N)!=="svelte-1fslf3g"&&(N.textContent=Tl),is=a(e),p(S.$$.fragment,e),ps=a(e),p(R.$$.fragment,e),rs=a(e),q=y(e,"P",{"data-svelte-h":!0}),d(q)!=="svelte-6qnode"&&(q.innerHTML=gl),os=a(e),Q=y(e,"P",{"data-svelte-h":!0}),d(Q)!=="svelte-fj8ans"&&(Q.textContent=$l),ms=a(e),E=y(e,"OL",{"data-svelte-h":!0}),d(E)!=="svelte-u1rnqj"&&(E.innerHTML=wl),cs=a(e),p(Y.$$.fragment,e),Ms=a(e),F=y(e,"P",{"data-svelte-h":!0}),d(F)!=="svelte-d7f48i"&&(F.innerHTML=hl),ys=a(e),U=y(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),d(U)!=="svelte-6riib1"&&(U.innerHTML=Ul),ds=a(e),p(X.$$.fragment,e),us=a(e),L=y(e,"UL",{"data-svelte-h":!0}),d(L)!=="svelte-1fi67i3"&&(L.innerHTML=bl),Js=a(e),p(_.$$.fragment,e),js=a(e),P=y(e,"UL",{"data-svelte-h":!0}),d(P)!=="svelte-1m9t4l7"&&(P.innerHTML=xl),fs=a(e),p(D.$$.fragment,e),Ts=a(e),O=y(e,"UL",{"data-svelte-h":!0}),d(O)!=="svelte-18zrfeh"&&(O.innerHTML=Cl),gs=a(e),p(K.$$.fragment,e),$s=a(e),ee=y(e,"UL",{"data-svelte-h":!0}),d(ee)!=="svelte-13d7alr"&&(ee.innerHTML=Il),ws=a(e),se=y(e,"P",{"data-svelte-h":!0}),d(se)!=="svelte-1dba84e"&&(se.textContent=Bl),hs=a(e),p(le.$$.fragment,e),Us=a(e),te=y(e,"P",{"data-svelte-h":!0}),d(te)!=="svelte-1h826ok"&&(te.innerHTML=vl),bs=a(e),p(ne.$$.fragment,e),xs=a(e),p(ae.$$.fragment,e),Cs=a(e),b=y(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),d(b)!=="svelte-jny9io"&&(b.innerHTML=Gl),Is=a(e),p(ie.$$.fragment,e),Bs=a(e),p(pe.$$.fragment,e),vs=a(e),p(re.$$.fragment,e),Gs=a(e),oe=y(e,"P",{"data-svelte-h":!0}),d(oe)!=="svelte-wqk7p2"&&(oe.innerHTML=Zl),Zs=a(e),p(me.$$.fragment,e),Ws=a(e),ce=y(e,"P",{"data-svelte-h":!0}),d(ce)!=="svelte-179w94s"&&(ce.innerHTML=Wl),ks=a(e),p(Me.$$.fragment,e),Hs=a(e),p(ye.$$.fragment,e),Vs=a(e),p(de.$$.fragment,e),As=a(e),ue=y(e,"P",{"data-svelte-h":!0}),d(ue)!=="svelte-rlihwg"&&(ue.innerHTML=kl),zs=a(e),p(Je.$$.fragment,e),Ns=a(e),p(je.$$.fragment,e),Ss=a(e),p(fe.$$.fragment,e),Rs=a(e),p(Te.$$.fragment,e),qs=a(e),p(ge.$$.fragment,e),Qs=a(e),p($e.$$.fragment,e),Es=a(e),p(we.$$.fragment,e),Ys=a(e),p(he.$$.fragment,e),Fs=a(e),p(Ue.$$.fragment,e),Xs=a(e),p(be.$$.fragment,e),Ls=a(e),xe=y(e,"P",{"data-svelte-h":!0}),d(xe)!=="svelte-iax3r4"&&(xe.textContent=Hl),_s=a(e),p(Ce.$$.fragment,e),Ps=a(e),p(Ie.$$.fragment,e),Ds=a(e),p(Be.$$.fragment,e),Os=a(e),p(ve.$$.fragment,e),Ks=a(e),p(Ge.$$.fragment,e),el=a(e),p(Ze.$$.fragment,e),sl=a(e),p(We.$$.fragment,e),ll=a(e),p(ke.$$.fragment,e),tl=a(e),p(He.$$.fragment,e),nl=a(e),Ve=y(e,"P",{"data-svelte-h":!0}),d(Ve)!=="svelte-2cmzpg"&&(Ve.textContent=Vl),al=a(e),p(Ae.$$.fragment,e),il=a(e),ze=y(e,"P",{"data-svelte-h":!0}),d(ze)!=="svelte-1tf2xx1"&&(ze.innerHTML=Al),pl=a(e),p(Ne.$$.fragment,e),rl=a(e),qe=y(e,"P",{}),Nl(qe).forEach(l),this.h()},h(){f(j,"name","hf:doc:metadata"),f(j,"content",Kl),f($,"class","tip"),Rl(w.src,dl="https://huggingface.co/datasets/huggingface-course/documentation-images/resolve/main/en/chapter1/companies.PNG")||f(w,"src",dl),f(w,"alt","Empresas que usan Hugging Face"),f(w,"width","100%"),f(h,"class","tip"),f(U,"class","tip"),f(b,"class","tip")},m(e,s){Fl(document.head,j),t(e,Se,s),t(e,T,s),t(e,Re,s),r(g,e,s),t(e,Qe,s),r(x,e,s),t(e,Ee,s),r(C,e,s),t(e,Ye,s),r(I,e,s),t(e,Fe,s),t(e,B,s),t(e,Xe,s),t(e,$,s),t(e,Le,s),r(v,e,s),t(e,_e,s),t(e,G,s),t(e,Pe,s),t(e,w,s),t(e,De,s),t(e,Z,s),t(e,Oe,s),t(e,h,s),t(e,Ke,s),t(e,W,s),t(e,es,s),r(k,e,s),t(e,ss,s),r(H,e,s),t(e,ls,s),t(e,V,s),t(e,ts,s),r(A,e,s),t(e,ns,s),r(z,e,s),t(e,as,s),t(e,N,s),t(e,is,s),r(S,e,s),t(e,ps,s),r(R,e,s),t(e,rs,s),t(e,q,s),t(e,os,s),t(e,Q,s),t(e,ms,s),t(e,E,s),t(e,cs,s),r(Y,e,s),t(e,Ms,s),t(e,F,s),t(e,ys,s),t(e,U,s),t(e,ds,s),r(X,e,s),t(e,us,s),t(e,L,s),t(e,Js,s),r(_,e,s),t(e,js,s),t(e,P,s),t(e,fs,s),r(D,e,s),t(e,Ts,s),t(e,O,s),t(e,gs,s),r(K,e,s),t(e,$s,s),t(e,ee,s),t(e,ws,s),t(e,se,s),t(e,hs,s),r(le,e,s),t(e,Us,s),t(e,te,s),t(e,bs,s),r(ne,e,s),t(e,xs,s),r(ae,e,s),t(e,Cs,s),t(e,b,s),t(e,Is,s),r(ie,e,s),t(e,Bs,s),r(pe,e,s),t(e,vs,s),r(re,e,s),t(e,Gs,s),t(e,oe,s),t(e,Zs,s),r(me,e,s),t(e,Ws,s),t(e,ce,s),t(e,ks,s),r(Me,e,s),t(e,Hs,s),r(ye,e,s),t(e,Vs,s),r(de,e,s),t(e,As,s),t(e,ue,s),t(e,zs,s),r(Je,e,s),t(e,Ns,s),r(je,e,s),t(e,Ss,s),r(fe,e,s),t(e,Rs,s),r(Te,e,s),t(e,qs,s),r(ge,e,s),t(e,Qs,s),r($e,e,s),t(e,Es,s),r(we,e,s),t(e,Ys,s),r(he,e,s),t(e,Fs,s),r(Ue,e,s),t(e,Xs,s),r(be,e,s),t(e,Ls,s),t(e,xe,s),t(e,_s,s),r(Ce,e,s),t(e,Ps,s),r(Ie,e,s),t(e,Ds,s),r(Be,e,s),t(e,Os,s),r(ve,e,s),t(e,Ks,s),r(Ge,e,s),t(e,el,s),r(Ze,e,s),t(e,sl,s),r(We,e,s),t(e,ll,s),r(ke,e,s),t(e,tl,s),r(He,e,s),t(e,nl,s),t(e,Ve,s),t(e,al,s),r(Ae,e,s),t(e,il,s),t(e,ze,s),t(e,pl,s),r(Ne,e,s),t(e,rl,s),t(e,qe,s),ol=!0},p(e,[s]){const zl={};s&1&&(zl.fw=e[0]),g.$set(zl)},i(e){ol||(o(g.$$.fragment,e),o(x.$$.fragment,e),o(C.$$.fragment,e),o(I.$$.fragment,e),o(v.$$.fragment,e),o(k.$$.fragment,e),o(H.$$.fragment,e),o(A.$$.fragment,e),o(z.$$.fragment,e),o(S.$$.fragment,e),o(R.$$.fragment,e),o(Y.$$.fragment,e),o(X.$$.fragment,e),o(_.$$.fragment,e),o(D.$$.fragment,e),o(K.$$.fragment,e),o(le.$$.fragment,e),o(ne.$$.fragment,e),o(ae.$$.fragment,e),o(ie.$$.fragment,e),o(pe.$$.fragment,e),o(re.$$.fragment,e),o(me.$$.fragment,e),o(Me.$$.fragment,e),o(ye.$$.fragment,e),o(de.$$.fragment,e),o(Je.$$.fragment,e),o(je.$$.fragment,e),o(fe.$$.fragment,e),o(Te.$$.fragment,e),o(ge.$$.fragment,e),o($e.$$.fragment,e),o(we.$$.fragment,e),o(he.$$.fragment,e),o(Ue.$$.fragment,e),o(be.$$.fragment,e),o(Ce.$$.fragment,e),o(Ie.$$.fragment,e),o(Be.$$.fragment,e),o(ve.$$.fragment,e),o(Ge.$$.fragment,e),o(Ze.$$.fragment,e),o(We.$$.fragment,e),o(ke.$$.fragment,e),o(He.$$.fragment,e),o(Ae.$$.fragment,e),o(Ne.$$.fragment,e),ol=!0)},o(e){m(g.$$.fragment,e),m(x.$$.fragment,e),m(C.$$.fragment,e),m(I.$$.fragment,e),m(v.$$.fragment,e),m(k.$$.fragment,e),m(H.$$.fragment,e),m(A.$$.fragment,e),m(z.$$.fragment,e),m(S.$$.fragment,e),m(R.$$.fragment,e),m(Y.$$.fragment,e),m(X.$$.fragment,e),m(_.$$.fragment,e),m(D.$$.fragment,e),m(K.$$.fragment,e),m(le.$$.fragment,e),m(ne.$$.fragment,e),m(ae.$$.fragment,e),m(ie.$$.fragment,e),m(pe.$$.fragment,e),m(re.$$.fragment,e),m(me.$$.fragment,e),m(Me.$$.fragment,e),m(ye.$$.fragment,e),m(de.$$.fragment,e),m(Je.$$.fragment,e),m(je.$$.fragment,e),m(fe.$$.fragment,e),m(Te.$$.fragment,e),m(ge.$$.fragment,e),m($e.$$.fragment,e),m(we.$$.fragment,e),m(he.$$.fragment,e),m(Ue.$$.fragment,e),m(be.$$.fragment,e),m(Ce.$$.fragment,e),m(Ie.$$.fragment,e),m(Be.$$.fragment,e),m(ve.$$.fragment,e),m(Ge.$$.fragment,e),m(Ze.$$.fragment,e),m(We.$$.fragment,e),m(ke.$$.fragment,e),m(He.$$.fragment,e),m(Ae.$$.fragment,e),m(Ne.$$.fragment,e),ol=!1},d(e){e&&(l(Se),l(T),l(Re),l(Qe),l(Ee),l(Ye),l(Fe),l(B),l(Xe),l($),l(Le),l(_e),l(G),l(Pe),l(w),l(De),l(Z),l(Oe),l(h),l(Ke),l(W),l(es),l(ss),l(ls),l(V),l(ts),l(ns),l(as),l(N),l(is),l(ps),l(rs),l(q),l(os),l(Q),l(ms),l(E),l(cs),l(Ms),l(F),l(ys),l(U),l(ds),l(us),l(L),l(Js),l(js),l(P),l(fs),l(Ts),l(O),l(gs),l($s),l(ee),l(ws),l(se),l(hs),l(Us),l(te),l(bs),l(xs),l(Cs),l(b),l(Is),l(Bs),l(vs),l(Gs),l(oe),l(Zs),l(Ws),l(ce),l(ks),l(Hs),l(Vs),l(As),l(ue),l(zs),l(Ns),l(Ss),l(Rs),l(qs),l(Qs),l(Es),l(Ys),l(Fs),l(Xs),l(Ls),l(xe),l(_s),l(Ps),l(Ds),l(Os),l(Ks),l(el),l(sl),l(ll),l(tl),l(nl),l(Ve),l(al),l(il),l(ze),l(pl),l(rl),l(qe)),l(j),c(g,e),c(x,e),c(C,e),c(I,e),c(v,e),c(k,e),c(H,e),c(A,e),c(z,e),c(S,e),c(R,e),c(Y,e),c(X,e),c(_,e),c(D,e),c(K,e),c(le,e),c(ne,e),c(ae,e),c(ie,e),c(pe,e),c(re,e),c(me,e),c(Me,e),c(ye,e),c(de,e),c(Je,e),c(je,e),c(fe,e),c(Te,e),c(ge,e),c($e,e),c(we,e),c(he,e),c(Ue,e),c(be,e),c(Ce,e),c(Ie,e),c(Be,e),c(ve,e),c(Ge,e),c(Ze,e),c(We,e),c(ke,e),c(He,e),c(Ae,e),c(Ne,e)}}}const Kl='{"title":"Transformers, ¿qué pueden hacer?","local":"transformers-what-can-they-do","sections":[{"title":"Los Transformers están en todas partes","local":"transformers-are-everywhere","sections":[],"depth":2},{"title":"Trabajar con pipelines","local":"working-with-pipelines","sections":[],"depth":2},{"title":"Pipelines disponibles para distintas modalidades","local":"pipelines-disponibles-para-distintas-modalidades","sections":[{"title":"Pipelines de texto","local":"pipelines-de-texto","sections":[],"depth":3},{"title":"Pipelines de imagen","local":"pipelines-de-imagen","sections":[],"depth":3},{"title":"Pipelines de audio","local":"pipelines-de-audio","sections":[],"depth":3},{"title":"Pipelines multimodales","local":"pipelines-multimodales","sections":[],"depth":3}],"depth":2},{"title":"Clasificación zero-shot","local":"zero-shot-classification","sections":[],"depth":2},{"title":"Generación de texto","local":"text-generation","sections":[],"depth":2},{"title":"Usar cualquier modelo del Hub en un pipeline","local":"using-any-model-from-the-hub-in-a-pipeline","sections":[{"title":"Inference Providers","local":"inference-providers","sections":[],"depth":3}],"depth":2},{"title":"Rellenado de máscaras","local":"mask-filling","sections":[],"depth":2},{"title":"Reconocimiento de entidades nombradas","local":"named-entity-recognition","sections":[],"depth":2},{"title":"Question answering","local":"question-answering","sections":[],"depth":2},{"title":"Resumen automático","local":"summarization","sections":[],"depth":2},{"title":"Traducción","local":"translation","sections":[],"depth":2},{"title":"Pipelines de imagen y audio","local":"pipelines-de-imagen-y-audio","sections":[{"title":"Clasificación de imágenes","local":"clasificación-de-imágenes","sections":[],"depth":3},{"title":"Reconocimiento automático de voz","local":"reconocimiento-automático-de-voz","sections":[],"depth":3}],"depth":2},{"title":"Combinar datos de múltiples fuentes","local":"combinar-datos-de-múltiples-fuentes","sections":[],"depth":2},{"title":"Conclusión","local":"conclusión","sections":[],"depth":2}],"depth":1}';function et(ml,j,Se){let T="pt";return ql(()=>{const Re=new URLSearchParams(window.location.search);Se(0,T=Re.get("fw")||"pt")}),[T]}class rt extends Ql{constructor(j){super(),El(this,j,et,Ol,Sl,{})}}export{rt as component};