Guide-yakabatana mibvunzo · Pakati Nhanho

Whisper Speech Recognition Quiz

Whisper's mitauro yakawanda-yekuteerera-kune-mavara dhizaini, mabasa ayo akasarudzwa-chiratidzo, uye izvo zvakapamhama zvekudzidzisa zvinoitwa uye zvisingavimbise.

Nzira dzekutungamira dzinoenderanaKuzivikanwa Kwekutaura Kwezevezeve
Mubvunzo 1 ye 8

Whisper akadzidziswa maawa mangani?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Whisper akadzidziswa maawa mangani?
    • 680,000 maawa
    • 6,800 maawa
    • 68,000 maawa
    • 6.8 miriyoni maawa
  2. Ndeipi inomiririra yepakati iyo Whisper anoverengera kubva kune yakaomeswa odhiyo pamberi peencoder?
    • A mbishi waveform tensor
    • A log-Mel spectrogram
    • MFCC delta inoratidzira chete
    • Imwe-inopisa phoneme vector
  3. Ko imwe Whisper modhi inoita sei mabasa akawanda sekunyora uye kududzira?
    • Inotakura imwe yakasiyana modhi pabasa
    • Iyo inomhanya yakaparadzana-yakakwenenzverwa misoro inofanana
    • Special kukurumidza tokens inotsanangura basa panguva yekunyora
    • Vashandisi vanogadzirisa iyo spectrogram nemaoko
  4. Ndeipi yakazara neural architecture inoshandiswa Whisper?
    • A convolutional-chete network
    • A inodzokororwa LSTM stack
    • A diffusion model
    • A Transformer encoder-decoder
  5. Nei Whisper ichionekwa seyakanyanya kusimba kana ichienzaniswa neyekare ASR masisitimu?
    • Yakadzidziswa pane akasiyana, ane ruzha real-world web audio
    • Inongoshanda pa studio-yakachena audio
    • Iyo haishandisi kudzidza muchina
    • Inoda maikorofoni yakasarudzika
  6. Zviyero zvemhando yaWhisper zvakaburitswa pasi perezinesi ripi?
    • Proprietary, API-chete
    • MIT (yakavhurika sosi)
    • GPL isina kushandiswa kwekutengesa
    • Creative Commons isiri yakabva
  7. Approximately how long is each audio segment Whisper converts to a log-Mel spectrogram?
    • 3 seconds
    • 3 minutes
    • 30 seconds
    • Maminitsi makumi matatu
  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