audio-course/pr_228/en/_app/immutable/nodes/20.c1924fa2.js

import{s as re,n as se,o as oe}from"../chunks/scheduler.cd324960.js";import{S as me,i as fe,e as ee,s as n,c as s,h as le,a as te,d as a,b as r,f as ie,g as o,k as ne,l as pe,m as i,n as m,t as f,o as l,p}from"../chunks/index.d5c3adcc.js";import{C as $e,H as c,E as ce}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.8072ce1f.js";import{Q as z}from"../chunks/Question.1eb61ddc.js";function ue(ae){let $,L,A,N,u,B,g,M,h,U,d,F,w,H,x,V,b,Q,y,R,C,G,k,I,T,K,v,O,q,j,W,D,_,J,S,X,E,Y,P,Z;return u=new $e({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),g=new c({props:{title:"Check your understanding of the course material",local:"check-your-understanding-of-the-course-material",headingTag:"h1"}}),h=new c({props:{title:"1. What is a vocoder?",local:"1-what-is-a-vocoder",headingTag:"h3"}}),d=new z({props:{choices:[{text:"An additional neural network that turns the spectrogram output of a transformer into a waveform.",explain:"Correct! ",correct:!0},{text:"A type of transformer layer that is responsible for creating audio embeddings.",explain:""},{text:"An additional neural network that preprocesses speech audio to remove background noise",explain:""}]}}),w=new c({props:{title:"2. Wav2Vec2 is an example of",local:"2-wav2vec2-is-an-example-of",headingTag:"h3"}}),x=new z({props:{choices:[{text:"Seq2Seq architecture",explain:""},{text:"CNN architecture",explain:""},{text:"CTC architecture",explain:"Correct!",correct:!0}]}}),b=new c({props:{title:"3. What does a blank token in CTC algorithm do?",local:"3-what-does-a-blank-token-in-ctc-algorithm-do",headingTag:"h3"}}),y=new z({props:{choices:[{text:"Blank token indicates breaks between the individual words in the sentence.",explain:""},{text:"Blank token is a predicted token that serves as a hard boundary between groups of characters. It makes it possible to filter out the duplicate characters",explain:"Correct!",correct:!0},{text:"Blank token is used for sounds that do not match any tokens in the vocabulary, similar to <UNK> token for 'unknown'.",explain:""}]}}),C=new c({props:{title:"4. Which of the following statements about CTC models is FALSE?",local:"4-which-of-the-following-statements-about-ctc-models-is-false",headingTag:"h3"}}),k=new z({props:{choices:[{text:"CTC models use only the encoder part of the transformer architecture.",explain:""},{text:"Wav2Vec2 & HuBERT use the exact same architecture but are trained differently.",explain:""},{text:"CTC models tend to perform best for speech recognition compared to other architectures.",explain:"Correct!",correct:!0}]}}),T=new c({props:{title:"5. Whisper is an example of",local:"5-whisper-is-an-example-of",headingTag:"h3"}}),v=new z({props:{choices:[{text:"Seq2Seq architecture",explain:"Correct!",correct:!0},{text:"CNN architecture",explain:""},{text:"CTC architecture",explain:""}]}}),q=new c({props:{title:"6. What is the easiest way to perform audio classification?",local:"6-what-is-the-easiest-way-to-perform-audio-classification",headingTag:"h3"}}),W=new z({props:{choices:[{text:"Use encoder-decoder transformers on the audio waveform.",explain:""},{text:"Use spectrograms and treat the task as an image classification problem.",explain:"Correct!",correct:!0},{text:"Turn a CTC model into a general-purpose audio classifier by changing the labels and training it with a regular cross-entropy loss function.",explain:""}]}}),_=new c({props:{title:"7. True or false? When treating spectrograms as images for classification, you will always benefit from image data augmentation techniques, such as shifting an image, cropping it, or resizing.",local:"7-true-or-false-when-treating-spectrograms-as-images-for-classification-you-will-always-benefit-from-image-data-augmentation-techniques-such-as-shifting-an-image-cropping-it-or-resizing",headingTag:"h3"}}),S=new z({props:{choices:[{text:"True",explain:""},{text:"False",explain:"Correct!",correct:!0}]}}),E=new ce({props:{source:"https://github.com/huggingface/audio-transformers-course/blob/main/chapters/en/chapter3/quiz.mdx"}}),{c(){$=ee("meta"),L=n(),A=ee("p"),N=n(),s(u.$$.fragment),B=n(),s(g.$$.fragment),M=n(),s(h.$$.fragment),U=n(),s(d.$$.fragment),F=n(),s(w.$$.fragment),H=n(),s(x.$$.fragment),V=n(),s(b.$$.fragment),Q=n(),s(y.$$.fragment),R=n(),s(C.$$.fragment),G=n(),s(k.$$.fragment),I=n(),s(T.$$.fragment),K=n(),s(v.$$.fragment),O=n(),s(q.$$.fragment),j=n(),s(W.$$.fragment),D=n(),s(_.$$.fragment),J=n(),s(S.$$.fragment),X=n(),s(E.$$.fragment),Y=n(),P=ee("p"),this.h()},l(e){const t=le("svelte-u9bgzb",document.head);$=te(t,"META",{name:!0,content:!0}),t.forEach(a),L=r(e),A=te(e,"P",{}),ie(A).forEach(a),N=r(e),o(u.$$.fragment,e),B=r(e),o(g.$$.fragment,e),M=r(e),o(h.$$.fragment,e),U=r(e),o(d.$$.fragment,e),F=r(e),o(w.$$.fragment,e),H=r(e),o(x.$$.fragment,e),V=r(e),o(b.$$.fragment,e),Q=r(e),o(y.$$.fragment,e),R=r(e),o(C.$$.fragment,e),G=r(e),o(k.$$.fragment,e),I=r(e),o(T.$$.fragment,e),K=r(e),o(v.$$.fragment,e),O=r(e),o(q.$$.fragment,e),j=r(e),o(W.$$.fragment,e),D=r(e),o(_.$$.fragment,e),J=r(e),o(S.$$.fragment,e),X=r(e),o(E.$$.fragment,e),Y=r(e),P=te(e,"P",{}),ie(P).forEach(a),this.h()},h(){ne($,"name","hf:doc:metadata"),ne($,"content",ge)},m(e,t){pe(document.head,$),i(e,L,t),i(e,A,t),i(e,N,t),m(u,e,t),i(e,B,t),m(g,e,t),i(e,M,t),m(h,e,t),i(e,U,t),m(d,e,t),i(e,F,t),m(w,e,t),i(e,H,t),m(x,e,t),i(e,V,t),m(b,e,t),i(e,Q,t),m(y,e,t),i(e,R,t),m(C,e,t),i(e,G,t),m(k,e,t),i(e,I,t),m(T,e,t),i(e,K,t),m(v,e,t),i(e,O,t),m(q,e,t),i(e,j,t),m(W,e,t),i(e,D,t),m(_,e,t),i(e,J,t),m(S,e,t),i(e,X,t),m(E,e,t),i(e,Y,t),i(e,P,t),Z=!0},p:se,i(e){Z||(f(u.$$.fragment,e),f(g.$$.fragment,e),f(h.$$.fragment,e),f(d.$$.fragment,e),f(w.$$.fragment,e),f(x.$$.fragment,e),f(b.$$.fragment,e),f(y.$$.fragment,e),f(C.$$.fragment,e),f(k.$$.fragment,e),f(T.$$.fragment,e),f(v.$$.fragment,e),f(q.$$.fragment,e),f(W.$$.fragment,e),f(_.$$.fragment,e),f(S.$$.fragment,e),f(E.$$.fragment,e),Z=!0)},o(e){l(u.$$.fragment,e),l(g.$$.fragment,e),l(h.$$.fragment,e),l(d.$$.fragment,e),l(w.$$.fragment,e),l(x.$$.fragment,e),l(b.$$.fragment,e),l(y.$$.fragment,e),l(C.$$.fragment,e),l(k.$$.fragment,e),l(T.$$.fragment,e),l(v.$$.fragment,e),l(q.$$.fragment,e),l(W.$$.fragment,e),l(_.$$.fragment,e),l(S.$$.fragment,e),l(E.$$.fragment,e),Z=!1},d(e){e&&(a(L),a(A),a(N),a(B),a(M),a(U),a(F),a(H),a(V),a(Q),a(R),a(G),a(I),a(K),a(O),a(j),a(D),a(J),a(X),a(Y),a(P)),a($),p(u,e),p(g,e),p(h,e),p(d,e),p(w,e),p(x,e),p(b,e),p(y,e),p(C,e),p(k,e),p(T,e),p(v,e),p(q,e),p(W,e),p(_,e),p(S,e),p(E,e)}}}const ge='{"title":"Check your understanding of the course material","local":"check-your-understanding-of-the-course-material","sections":[{"title":"1. What is a vocoder?","local":"1-what-is-a-vocoder","sections":[],"depth":3},{"title":"2. Wav2Vec2 is an example of","local":"2-wav2vec2-is-an-example-of","sections":[],"depth":3},{"title":"3. What does a blank token in CTC algorithm do?","local":"3-what-does-a-blank-token-in-ctc-algorithm-do","sections":[],"depth":3},{"title":"4. Which of the following statements about CTC models is FALSE?","local":"4-which-of-the-following-statements-about-ctc-models-is-false","sections":[],"depth":3},{"title":"5. Whisper is an example of","local":"5-whisper-is-an-example-of","sections":[],"depth":3},{"title":"6. What is the easiest way to perform audio classification?","local":"6-what-is-the-easiest-way-to-perform-audio-classification","sections":[],"depth":3},{"title":"7. True or false? When treating spectrograms as images for classification, you will always benefit from image data augmentation techniques, such as shifting an image, cropping it, or resizing.","local":"7-true-or-false-when-treating-spectrograms-as-images-for-classification-you-will-always-benefit-from-image-data-augmentation-techniques-such-as-shifting-an-image-cropping-it-or-resizing","sections":[],"depth":3}],"depth":1}';function he(ae){return oe(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ye extends me{constructor($){super(),fe(this,$,he,ue,re,{})}}export{ye as component};