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.
Ikibazo 1 Bya 8
Niyihe ntego nyamukuru ya __AIU_PROTECTED_10 __ 'Kwongorera?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- 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
- 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
- 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
- Ni ubuhe bushobozi Whisper NTIBISANZWE?
- Guhindura imvugo mu zindi ndimi mucyongereza
- Kumenya ururimi ruvugwa
- Ongeraho ingengabihe kuri transcript
- Gukora videwo ifatika uhereye mukanya
- 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
- 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
- Approximately what share of Whisper’s training data was English audio paired with English transcripts?
- About 18%
- Hafi ya 1%
- About 65%
- About 100%
- 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