Guide-yakabatana mibvunzo · Pakati Nhanho

Moshi Yakazara-Duplex Yekutaura Quiz

Inotarisa Moshi's full-duplex audio hova, Mimi codec, yakananga kutaura-kune-kutaura dhizaini, latency chinangwa uye yemukati-monologue nzira.

Nzira dzekutungamira dzinoenderanaMoshi Yakazara Duplex Kutaura
Mubvunzo 1 ye 8

Chii chinonzi 'full-duplex' muchirevo chechinyorwa cheMoshi?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinonzi 'full-duplex' muchirevo chechinyorwa cheMoshi?
    • Inogona kuteerera uye kutaura panguva imwe chete
    • Inongoshanda mumitauro miviri chete
    • Inoda maikorofoni maviri
    • Inowedzera kaviri vhoriyamu yekuteerera
  2. Isangano ripi rakaburitsa Moshi?
    • OpenAI
    • Kyutai
    • Google DeepMind
    • Meta
  3. Chii chinonzi Mimi muMoshi system?
    • Injini yekutsvaga
    • A graphics renderer
    • A neural audio codec inoshandura kutaura kuita discrete tokeni
    • Purogiramu yekushandura mashoko
  4. Ko Moshi inosiyana sei nepombi yechinyakare inotsigira izwi?
    • Inoburitsa zvinyorwa chete
    • Hazvidi modhi zvachose
    • Inoshanda chete kunze kwenyika pasina AI
    • Inoita odhiyo zvakananga panzvimbo yekuisa chain STT, LLM, uye TTS
  5. Moshi anonangana nekutaura kunonoka kupi?
    • Around 160-200 milliseconds
    • Anenge 2-3 masekondi
    • Zvinenge gumi masekonzi
    • 1 miniti chaiyo
  6. Chii chinangwa cheMoshi's 'Inner Monologue' nzira?
    • Kuvanza nhaurirano kubva kune vashandisi
    • Kufanotaura zvinyorwa zvisati zvaitika, kuvandudza mhando yemitauro
    • Kuturikira zvese muchiFrench
    • Kumanikidza vhidhiyo
  7. Mimi encodes audio at 12.5 discrete frames per second. About how far apart are consecutive frames?
    • About 8 milliseconds
    • About 800 milliseconds
    • About 80 milliseconds
    • About 1 second
  8. Which two synchronized streams does Moshi model in parallel?
    • Two unrelated text transcripts
    • The user’s video and the system’s screen
    • Two copies of the same language-model weights
    • The user’s incoming audio and the system’s own outgoing audio