Kediska Aqoonsiga Hadalka Shaqsiga

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Qiyaastii imisa saacadood oo maqal ah ayaa lagu tababaray Whisper?
   • 680,000 saacadood
   • 6,800 saacadood
   • 68,000 saacadood
   • 6.8 milyan saacadood
2. Waa maxay matalaada dhexe ee Whisper ka xisaabinaysa codka qaydhiin ka hor codeeyaha?
   • Tensor waveform cayriin
   • A log-Mel spectrogram
   • MCCC delta sifooyinka kaliya
   • Hal-kulan Phoneme vector
3. Sidee buu hal nooc oo Whisper ah u qabtaa hawlo badan sida qorista iyo tarjumaada?
   • Waxay ku raran tahay nooc ka duwan hawl kasta
   • Waxay wada madax gaar ah oo toosan oo is barbar socda
   • Calaamadaha degdega ah ee gaarka ah ayaa tilmaamaya hawsha marka la kala saarayo
   • Isticmaalayaasha ayaa gacanta ku tafatira spectrogramka
4. Waa maxay qaab dhismeedka neerfaha guud ee uu Whisper adeegsato?
   • Shabakad kacaan-kaliya
   • Xidhmo LSTM ah oo soo noqnoqda
   • Qaab fidin
   • Beddelka codeeyaha
5. Waa maxay sababta Whisper loogu tixgaliyo inay si gaar ah u adag tahay marka la barbar dhigo nidaamyada hore ee ASR?
   • Waxaa lagu tababaray kala duwan, dhawaaqa mareegaha dhabta ah ee buuqa badan
   • Waxa kaliya oo ay ku shaqeysaa cod nadiif ah istuudiyaha
   • Ma isticmaalo barashada mashiinka
   • Waxay u baahan tahay makarafoon gaar ah
6. Shatiga noocee ah ayaa lagu sii daayay miisaanka model Whisper?
   • Lahaanshaha, API-kaliya
   • MIT (ilo furan)
   • GPL oo aan la isticmaalin ganacsi
   • Hal-abuurka Caadiga ah ee aan ka soo bixin
7. Approximately how long is each audio segment Whisper converts to a log-Mel spectrogram?
   • 3 seconds
   • 3 minutes
   • 30 seconds
   • 30 daqiiqo
8. What does Whisper’s English-translation task produce from non-English speech?
   • A translated recording in the speaker’s voice
   • Only a transcript in the original language
   • A list of detected speakers
   • An English text translation