Audio AI JAGORA

Kunkuru TTS Autoregressive Synthesis

Tortoise TTS tsari ne na bude tushen rubutu-zuwa-magana da aka samu don yanayin da ba a saba gani ba, muryoyi masu wadatar zuci da sautin murya mai ƙarfi daga ƴan gajerun shirye-shiryen bidiyo.

2 min karatuAn sabunta ta ƙarshe

Dubawa

Its name is a wink at the trade-off: it is slow but produces remarkably high-quality speech.

Zurfafa nutsewa

James Betker ne ya ƙirƙira kuma aka sake shi a cikin 2022, Tortoise TTS ya aro ra'ayoyi daga tsarar hoto, musamman na'urorin lantarki da watsawa, kuma ya yi amfani da su ga magana. Idan aka ba ɗan gajeren faifan bidiyo na muryar da aka yi niyya, zai iya haɗa wannan muryar kuma ya karanta rubutu na sabani tare da gamsarwa, motsa jiki, da motsin rai. Da gangan yana fifita inganci fiye da gudu, wanda shine dalilin da yasa tsara na iya ɗaukar daƙiƙa da yawa a kowace magana, don haka misalin kunkuru. Tortoise yana haifar da fitattun 'yan takara da yawa kuma yana amfani da ƙirar ƙira don zaɓar mafi aminci. Ya zama al'umma da aka fi so don muryoyin murya, fan dubs, da bincike saboda buɗaɗɗen ma'aunin nauyi ya ba kowa damar yin gwaji, kuma yanayin sa ya yi hamayya da tsarin kasuwanci na zamaninsa.

Fahimtar Fasaha

Tortoise yana haɗa na'urar ta atomatik wanda ke yin tsinkayar alamun magana da aka sharadi akan rubutu da abin da aka haɗa murya, sannan ya sake sabunta waɗancan alamun tare da na'urar diffusion don samar da mel-spectrogram, a ƙarshe an ƙirƙira su cikin sauti. Samfurin maƙirari daban-daban na CLVP ya ƙirƙira tsararrun ƴan takara da yawa akan rubutu, don haka tsarin zai iya yin samfuri da yawa kuma ya kiyaye mafi kyawun lokaci, ƙididdige lokacin ciniki don aminci.

Dabarun Tasiri

Shiga ku isa

Yana inganta samun dama ta hanyar rubutu, ba da labari, da mu'amalar murya.

Kudin da kasafin kuɗi

Ƙungiyoyin kafofin watsa labaru na iya jigilar sauti mai gogewa cikin sauri tare da ƙaramin kasafin kuɗi.

Gudu da sikelin

Tsarin fuskantar abokin ciniki na iya aiwatar da hulɗar magana a mafi girman ma'auni.

Makomar Tortoise TTS Autoregressive Synthesis

Kunkuru ya zaburar da guguwar magada cikin sauri da cokali mai yatsu da nufin kiyaye ingancin sa yayin yanke latency, da dabarunsa sun yi tasiri a tsarin cloning daga baya. Jagoran gaba a bayyane yake: adana yanayin matakin Tortoise yayin da yake gabatowa cikin sauri na ainihin lokaci, ƙara ingantaccen motsin rai da kulawa mai salo, da haɗa irin waɗannan buɗaɗɗen ƙira tare da yarda da kiyaye alamar ruwa yayin da sautin murya ya zama na yau da kullun kuma ana bincikar da'a.

Aiwatar da Gaskiyar Duniya

Rufe muryar mai ba da labari daga gajerun samfura don karanta rubutun dogon tsari

Ƙirƙirar muryoyin bayyananniyar murya don fan dubs da ayyukan rayarwa

Samar da keɓaɓɓen saƙonnin odiyo ko ba da labari

Yin hidima azaman tushen bincike don nazarin haɗakar magana ta autoregressive

Hatsari & Tsare-tsare

Rashin amfani da murya da haɗarin kwaikwaya yana ƙaruwa lokacin da aka rasa izini.

Daidaituwa na iya faɗuwa cikin lafuzza, yaruka, ko mahalli masu hayaniya.

Ana iya kuskuren sauti na roba don ingantacciyar magana ba tare da bayyananniyar lakabi ba.

Taswirar Hanya

1

Sami tabbataccen izini don ɗaukar murya, cloning, da sake amfani.

2

Gwajin ingantattun masu magana daban-daban da yanayin baya.

3

Ƙayyade lokacin da dole ne ɗan adam ya duba ko ya amince da abubuwan da aka fitar.

4

Yi lakabin sauti na roba da kuma adana bayanan da aka tabbatar don yin lissafi.

Ci gaba da Bincike

Free newsletter

Get the daily AI briefing

Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.

One email each weekday. Unsubscribe in one click. We never sell or share your address.

Test yourself

Take the Tortoise TTS Autoregressive Synthesis quiz

Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.

Fara tambayoyi

Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation

Jagora na gaba

FastSpeech da Mara-autoregressive TTS

Tambayoyin da ake yawan yi

What is Tortoise TTS Autoregressive Synthesis?

Tortoise TTS tsari ne na bude tushen rubutu-zuwa-magana da aka samu don yanayin da ba a saba gani ba, muryoyi masu wadatar zuci da sautin murya mai ƙarfi daga ƴan gajerun shirye-shiryen bidiyo. Sunan sa ido-da-ido ne a cinikin: yana da hankali amma yana samar da magana mai inganci.

Menene sunan Tortoise TTS nufi?

Misalin kunkuru yana nuna gangancin cinikin sa na jinkirin tsara don samar da yanayi na zahiri.

Menene Tortoise zai iya yi da ƴan gajerun shirye-shiryen bidiyo?

Tortoise yana yin ƙulliyar murya kaɗan, yana sake fitar da murya daga ɗimbin gajerun samfura.

Wadanne iyalai biyu ne suka fi yin tasiri akan ƙirar Tortoise?

Kunkuru ya daidaita masu taswira na autoregressive da dabarun yadawa daga tsara hoto zuwa magana.

Ta yaya Tortoise ke zaɓar tsakanin ƴan takara da aka ƙirƙira?

Samfurin zura kwallaye na CLVP yana ba da matsayi ga tsararrakin 'yan takara don aminci, yana barin Tortoise ya kiyaye mafi kyawun ɗauka.

Wanene ya halicci Tortoise TTS?

James Betker ne ya kirkiro Tortoise TTS kuma an sake shi kusan 2022.