quiz bu lëkkale ak tegtal · Diggante Niveau

Déglu te jaare ci Quiz bi

Xoolaat LAS déglukat-ortograafi jëmmal, piramidal waxtu wàññi, bàyyi xel, génnug araf, ak jàngat këyit bu njëkk.

Yooni njiit yu jëm ciDéglu Tekki ak Bind
Laaj 1 de 8

Lan mooy ñaari mbir yi gëna am solo ci xeetu LAS?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan mooy ñaari mbir yi gëna am solo ci xeetu LAS?
    • Déglukat ak bindkat
    • Enkoder ak tokenisatër
    • Generatër ak tànneef
    • Seggal ak xaajkat
  2. Lu Speller bi ci LAS di génne?
    • Fonem yu bawoo ci diksoneer
    • Personaas yi, benn-benn
    • Baatu lëmm kese
    • Spectre fréquence
  3. Lu tax ñuy woowe enkodeer LAS 'piramidal'?
    • Dafa am formu triangle ci kaw ekraŋ bi
    • Dafay jëfandikoo ñetti GPU
    • Dafay wàññi diir bi ci dayo bu nekk
    • Dafay piramid valeur perte yi
  4. Ban composant bu yàgg la LAS soxlawul?
    • Mikro
    • fonction perte
    • Done tàggat yaram
    • Diksionaari waxin fonem yuñ defaree loxo
  5. Ban jumtukaay mooy may Speller mu bàyyi xelam ci wàll wi war ci audio bi ci araf bu nekk?
    • Fexe
    • Dàddu
    • Normalisasioŋ ci lots
    • Daggukaayu traverse
  6. Lan mooy benn ci ay gàttal ci xeetu LAS bi njëkk?
    • Mënul dox ci benn aparey
    • Du woon streaming, fàww nga wax lépp balaa nga koy dekode
    • Dafay génne ay nimero kese
    • Dafay laaj diksoneer fonem
  7. What WER did the LAS paper report on its Google voice-search subset without a language model?
    • 1.41%
    • 41.0%
    • 14.1%
    • 80.0%
  8. What distinction does the LAS paper make about dependencies among output characters?
    • It predicts each character independently with no sequence model
    • It outputs only phoneme classes and forbids character context
    • It requires a separate dictionary to define character dependencies
    • The model emits character sequences without assuming the characters are independent