Chidzidzo cheAI yeRuzha

Moshi Yakazara-Duplex Kutaura

Moshi ndeye yakavhurika-sosi, chaiyo-nguva izwi AI kubva kuKyutai inotaura uye inoteerera panguva imwe chete - yakazara-duplex - pane kutora majana akasimba.

Teerera kugwaro iriAI-yakarondedzerwa · ~2 min

Pa peji ino2 min verenga
  1. Pfupiso
  2. Kudzika Kwakadzika
  3. Kuitwa muNyika yeChokwadi
  4. Ramangwana reMoshi Yakazara-Duplex Kutaura
  5. Kuzvishandisa
  6. Ramba Uchiongorora
  7. Mibvunzo inowanzo bvunzwa

Pfupiso

That removes the awkward lag and rigid turn-taking of traditional voice assistants.

Kudzika Kwakadzika

Moshi, yakaburitswa neFrench lab Kyutai muna 2024, imhando yekutaura-ku-kutaura-nheyo yakavakirwa kune yakasikwa, yakaderera-latency hurukuro. Kusiyana nemapaipi vabatsiri vanobatanidza kutaura-kune-mavara, ipapo modhi yemutauro, ipapo mavara-kune-kutaura, Moshi inobata odhiyo zvakananga uye ichienderera. Pfungwa yayo yakakosha ndeye duplex yakazara: inoenzanisira maodhiyo hova maviri panguva imwe chete - yemushandisi neyayo - saka inogona kuteerera ichitaura, inobata zvinokanganisa, backchannel ine 'mhm,' uye inopindirana zvakasikwa sezvinoita vanhu. Iyo inosvika latency yakatenderedza 160-200 milliseconds, kure pasi peyakajairwa mubatsiri lag. Pasi pehodhi inobatanidza 7B-parameter mavara-uye-odhiyo mutauro modhi (Helium) naMimi, neural audio codec inomanikidza kutaura kuita ma tokeni akasarudzika anogona kuburitswa nemuenzaniso. Kyutai akaburitsa huremu nekodhi pachena.

Kuitwa muNyika yeChokwadi

Mufambidzani wezwi risina maoko iwe unogona kukanganisa pakati pemutsara, nemhinduro dziri pasi pe200 milliseconds.

Vhura hwaro hwekutsvagisa yekudzidza-chaiyo-nguva, yakazara-duplex inotaurwa nhaurirano isina mabhokisi matema evaridzi.

Kuwanikwa vabatsiri vanokurukura zvinyoro-nyoro nevashandisi vanoda nekukurumidza, zvakasikwa kumashure-uye-mberi.

Prototyping inovhiringidza mutengi-sevhisi izwi bots iyo backchannel uye inopindura munhu anenge afona achiri kutaura.

Ramangwana reMoshi Yakazara-Duplex Kutaura

Yakazara-duplex modelling iri kuita template yezvakasikwa izwi AI, inofurira masisitimu muindasitiri yese. Tarisira madiki, e-pa-mudziyo shanduro, rutsigiro rwemitauro yakawanda, yakaderera latency, uye kubatanidzwa muvamiririri, sevhisi yevatengi, uye maturusi ekuwanika. Nekuti Moshi yakavhurika, vaongorori vanogona kuongorora nekuivandudza vakasununguka. Matambudziko anoramba ari pamusoro pekuvimbika kwechokwadi, kuchengetedzeka mukutaura kunopindirana, uye nuance yemanzwiro, asi kusimuka kubva pakuomarara-kutora kuenda kumvura, kuvhiringika nhaurirano inogona kusingaperi.

Kuzvishandisa

Nei zvichikosha

  • Svika uye svika. Inonatsiridza kusvikika kuburikidza nekunyora, kurondedzera, uye mazwi ekubatanidza.
  • Mutengo uye bhajeti. Zvikwata zveMedia zvinogona kutumira odhiyo yakakwenenzverwa nekukurumidza nemabhajeti madiki.
  • Kumhanya uye chiyero. Masisitimu anotarisana nevatengi anogona kugadzirisa kutaurirana kwekutaura pamwero mukuru.

Chenjera

  • Kushandisa izwi zvisizvo uye njodzi dzekuedzesera dzinowedzera kana chibvumirano chisipo.
  • Kururama kunogona kudonha mumitauro, mataurirwo, kana nharaunda dzine ruzha.
  • Synthetic audio inogona kukanganisa kutaura kwechokwadi isina mavara akajeka.

Matanho anotevera

  1. Wana mvumo yakajeka yekutora inzwi, kugadzira, uye kushandisa zvakare.
  2. Yedza mhando pavatauri vakasiyana uye mamiriro ekumashure.
  3. Tsanangura apo munhu anofanira kuongorora kana kubvumidza zvabuda.
  4. Label synthetic odhiyo uye chengetedza marekodhi ekuzvidavirira.

Ramba Uchiongorora

Tsamba yemahara

Tora iyo yemazuva ese AI pfupiso

Nhatu dzakasimbiswa dzeAI nyaya mangwanani ega ega pakati pevhiki, dzakanyorwa neChirungu chakajeka. Yemahara zvachose, hapana ads.

Imwe email zuva rega rega revhiki. Bvisa kunyoresa kamwe chete. Hatimbotengese kana kugovera kero yako.

Zviedze iwe pachako

Take the Moshi Full-Duplex Speech quiz

Mhinduro yepakarepo pamhinduro yega yega, uye chitupa chinogovaniswa chine ID inobatika kana wapedza kosi.

Tanga mibvunzo

Tsigira dzidzo yemahara yeAI. AI Understanding ndeye 501(c)(3) isingabatsiri - hapana ads, hapana paywall, zvachose. Ita chipo

Mibvunzo inowanzo bvunzwa

What is Moshi Full-Duplex Speech?

Moshi ndeye yakavhurika-sosi, chaiyo-nguva izwi AI kubva kuKyutai inotaura uye inoteerera panguva imwe chete - yakazara-duplex - pane kutora majana akasimba. Izvo zvinobvisa kusadzikama uye kuomarara-kutora kwechinyakare vabatsiri vezwi.

Chii chinonzi 'full-duplex' muchirevo chechinyorwa cheMoshi?

Yakazara-duplex zvinoreva kuti modhi inobata odhiyo inouya uye inobuda panguva imwe chete, saka inogona kuteerera ichitaura uye kubata zvinovhiringa zvagara.

Isangano ripi rakaburitsa Moshi?

Moshi yakagadziriswa uye yakavhurika-yakavhurwa naKyutai, yeFrench AI yekutsvagisa lab, muna 2024.

Chii chinonzi Mimi muMoshi system?

Mimi ndiyo neural audio codec inomanikidza kuenderera kutaura kune yakaderera-bitrate rwizi rwe discrete tokens iyo modhi inogona kuburitsa.

Ko Moshi inosiyana sei nepombi yechinyakare inotsigira izwi?

Vabatsiri vetsika vanobatanidza kutaura-kune-mavara, muenzaniso wemutauro, uye zvinyorwa-ku-kutaura; Moshi imhando yekutaura-kune-kutaura inobata odhiyo nguva dzose.

Moshi anonangana nekutaura kunonoka kupi?

Moshi inowana latency yakatenderedza 160-200 ms, yakadzikira zvakanyanya pane yakajairwa vabatsiri vezwi, ichigonesa kupindirana kwechisikigo uye kukanganisa.