Ikibazo gihuza ibibazo · Hagati Urwego

OpenAI Ikibazo Cyongorerano

Ongera usubiremo Amahugurwa-amakuru yibigize, imyitwarire yindimi nyinshi, hamwe nuburyo bwo gutsindwa utiriwe wibwira ko inyandiko-mvugo ari nziza.

Inzira zijyanye no kuyoboraOpenai Kwongorera
Ikibazo 1 Bya 8

Niyihe ntego nyamukuru ya __AIU_PROTECTED_10 __ 'Kwongorera?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niyihe ntego nyamukuru ya __AIU_PROTECTED_10 __ 'Kwongorera?
    • Kumenyekanisha imvugo byikora: kwandukura no guhindura amajwi
    • Gukora amashusho kuva mwandiko
    • Kwandika kode ya mudasobwa
    • Gukora animasiyo ya 3D
  2. What was true of the language balance in Whisper’s training audio?
    • Every language contributed the same number of hours
    • The dataset was English-heavy, with much less audio for most languages
    • The dataset contained only English audio
    • Most data was studio-recorded speech in one language
  3. What does Whisper use to condition the decoder on the requested task and language?
    • A separate camera feed
    • A hand-written transcript of the answer
    • Special tokens in the decoder prompt
    • A unique model checkpoint for every utterance
  4. Ni ubuhe bushobozi Whisper NTIBISANZWE?
    • Guhindura imvugo mu zindi ndimi mucyongereza
    • Kumenya ururimi ruvugwa
    • Ongeraho ingengabihe kuri transcript
    • Gukora videwo ifatika uhereye mukanya
  5. Which long-form transcription problems does OpenAI’s paper describe?
    • Repetition loops and missing words near segment edges
    • Perfect diarization of every speaker
    • Automatic correction of every proper noun
    • Guaranteed removal of background music
  6. Nintege nke zizwi za Whisper kureba?
    • Ntishobora gutunganya amajwi yicyongereza
    • Irashobora rimwe na rimwe 'hallucinate' inyandiko itavuzwe
    • Isohora gusa amajwi, ntabwo yigeze yandika
    • Yanze kongeramo utumenyetso
  7. Approximately what share of Whisper’s training data was English audio paired with English transcripts?
    • About 18%
    • Hafi ya 1%
    • About 65%
    • About 100%
  8. What use does OpenAI caution against when transcription errors could have serious consequences?
    • Noncommercial experimentation with public samples
    • Ongeraho ingengabihe kuri transcript
    • Using the model to identify a language
    • High-risk decision-making without appropriate verification