Guide-yakabatana mibvunzo · Pakati Nhanho

OpenAI Mibvunzo yezevezeve

Ongorora Whisper kudzidziswa-dhata kuumbwa, maitiro emitauro yakawanda, uye zvakanyorwa kukundikana modhi pasina kufungidzira kuti zvinyorwa zvinogara zvakarurama.

Nzira dzekutungamira dzinoenderanaOpenai Whisper
Mubvunzo 1 ye 8

Chinangwa chikuru che OpenAI's Whisper chii?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chinangwa chikuru che OpenAI's Whisper chii?
    • Kuziva matauriro otomatiki: kunyora nekushandura odhiyo
    • Kugadzira mifananidzo kubva pane zvinyorwa
    • Kunyora kodhi yekombuta
    • Kugadzira 3D animations
  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. Ndeupi hunyanzvi hunopihwa Whisper NOT natively?
    • Kushandura mutauro kubva kune mimwe mitauro kuenda kuChirungu
    • Kutsvaga mutauro urikutaurwa
    • Kuwedzera zvitambi zvenguva kune chinyorwa
    • Kugadzira vhidhiyo yechokwadi kubva nekukurumidza
  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. Chii chinozivikanwa kushaya simba kweWhisper chekutarisa?
    • Haikwanise kugadzirisa chero Chirungu audio
    • Inogona kupota ichi 'illucinate' zvinyorwa zvisina kutaurwa
    • Inongoburitsa odhiyo chete, kwete mameseji
    • Zvinoramba kuwedzera nyora
  7. Approximately what share of Whisper’s training data was English audio paired with English transcripts?
    • About 18%
    • Zvingangoita 1%
    • About 65%
    • About 100%
  8. What use does OpenAI caution against when transcription errors could have serious consequences?
    • Noncommercial experimentation with public samples
    • Kuwedzera zvitambi zvenguva kune chinyorwa
    • Using the model to identify a language
    • High-risk decision-making without appropriate verification