OpenAI

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

1. Lan mooy jubluwaay bu mag bi ci OpenAI?
   • Xamme kàddu yi ci saa si: bind ak tekki kàddu yi
   • Defar ay nataal ci mbind
   • Bind kodu ordinatër
   • Defar ay animaasioŋ 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. Ban kàttan la Whisper DU joxe ci boppam?
   • Tekki kàddu yu bawoo ci yeneen làkk yi ci Àngle
   • Gis ban làkk lañuy wax
   • Yokk timestamp ci benn transkripsioŋ
   • Defar wideo yu dëggu ci ab laaj
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. Lan mooy ñakk kattan guñu xamee ci Whisper?
   • Mënul def benn audio ci Angale
   • Yenn saa muy 'hallucinate' mbind buñu waxul
   • Audio rek lay genne, du musa bind
   • Dafa bañ yokk ay ponksioŋ
7. Approximately what share of Whisper’s training data was English audio paired with English transcripts?
   • About 18%
   • Lu tollu ci 1%
   • About 65%
   • About 100%
8. What use does OpenAI caution against when transcription errors could have serious consequences?
   • Noncommercial experimentation with public samples
   • Yokk timestamp ci benn transkripsioŋ
   • Using the model to identify a language
   • High-risk decision-making without appropriate verification