VITS

Baker (Chinese)

Iinketho zelizwe IsiTshayina Neutral VITS

{igama} yi neutral AI yelizwi elinamandla eVITS umbhalo-kwi-speech model. Eli free-tier ilizwi lithetha IsiTshayina kwaye linika ngcono-quality speech synthesis. Nge Ixesha elifutshane unikezelo lwesantya kunye nomgangatho womgangatho we 3/5, Baker (Chinese) ulungele general-purpose text-to-speech with natural prosody. I-VITS injini iphuhliswe ngu Jaehyeon Kim et al. under the MIT license, iyenza ikhuseleke kwimisebenzi yentengiso. Iinkqubo eziphambili ziquka: {iimpawu}.

Akukho manqaku

VITSUlwazi lwemodeli

Imodeli VITS
Umbhekisi phambili Jaehyeon Kim et al.
Umgangatho
Isantya I-Fixed
Ilayisensi MIT
Ukuklona Ayifumaneki
I-Tier Iinketho ze projekti
Iiparamitha 25M
Uyilo lwezindlu VAE + Normalizing Flows + GAN
Uqeqesho lwe Data 585 iiyure
Iminyaka 2021

Iinkqubo ezilungileyo zokusetyenziswa Baker (Chinese)

Iinkqubo ezicetyiswayo ezisekelwe kwiimpawu zalo msindo

Iincwadi ezinesandi & Uxwebhu

Sebenzisa i {igama} ukuchaza imixholo yefom ende nge-prosody eqhelekileyo ne-expression.

Ividiyo

Yongeza ukuthetha okuzimeleyo kwiividiyo zeYouTube, iintengiso, kunye nemixholo yemidiya yoluntu.

Iinkqubo & Zokufikelela

Ukwenziwa ngokukhawuleza kwenza le lizwi lilungele iinkqubo zexesha elibonakalayo, abafundi bekhusi, kunye neezixhobo zokufikelela.

Ukufunda nge-e-mail & Uqeqesho

Yenza izinto zokuqeqesha ezibandakanyayo, izifundo, kunye nezinto eziqulethe ulwazi ngemiboniso ecacileyo ye-AI.

I-More VITS IiNkokheli

Ezinye iingoma zemodeli efanayo ye-TTS

Default

IsiNgesi Neutral

Imibuzo ebuzwa rhoqo

VITS (I-Variation Inference ne-adversarial learning for end-to-end Text-to-Speech) yindlela efana ne-end-to-end TTS evelisa isandi esininzi esiqhelekileyo kunezikhokelo zenqanaba elinye. Isebenzisa i-variation inference ephuculweyo ngokuhamba okuqhelekileyo kunye nenkqubo yoqeqesho oluchaphazelayo, efumana ukuphuculwa okubalulekileyo kwindalo.

I-VITS yaphuhliswa nguJaehyeon Kim nokunye. kwaye ikhutshwa phantsi kwelayisensi yeMIT, evumela ukusetyenziswa korhwebo lwesandi esiveliswe.

VITS inkxaso 4 ulwimi: IsiNgesi, isiTshayina, isiJaphani, isiKorea.

I-VITS ikwinqanaba elikhululekileyo - elikhululekileyo - akukho tyala lifunekayo. Ungajonga ngaphambili nayiphi na i-VITS yesandi ngaphandle kokuvelisa isandi esipheleleyo.

VITS inesantya esikhawulezayo kakhulu sokwakha. Isebenza kwixesha elifutshane elibonakalayo, iyenza ilungele unikezelo kunye nesicelo esisebenza ngokuthe ngqo.

I-VITS ilinganiselwe 3/5 kumgangatho wesandi kwi-TTS.ai. Inikezela ngomgangatho olungileyo wokuthetha olungele izicelo ezininzi.

Hayi, i-VITS isebenzisa iseti emiselweyo yelizwi elifakwe ngaphakathi. Ukwenza i-clone yelizwi, zama iimodeli ezinjenge-CosyVoice 2, GPT-SoVITS, okanye i-Chatterbox.

Ewe, i VITS icetyiswa ngokukodwa kwinjongo yomxholo-ukuthetha ngeprosody eqhelekileyo. Uhlobo lwesiphelo-siphelo, iprosody eqhelekileyo, uluhlu olukhawulezayo lweziphumo zenza ukuba ibe lukhetho olulungileyo kule meko yokusetyenziswa.

Ewe, i-VITS isemthethweni phantsi kwe-MIT, evumela ukusetyenziswa korhwebo. Isandi esiveliswe ngee-VITS zesandi singasetyenziswa kwiividiyo, iipodcasts, ii-apps, imidlalo, nakweyiphi na enye iprojekthi yorhwebo.

Ewe, zonke iingoma kwi-TTS.ai zisebenzisa iimodyuli ze-open-source ezilayisensiweyo ngentengiso (MIT, Apache 2.0). Isandi esiveliswe yiyo yakho ukuyisebenzisa kwividiyo, iipodcasts, iiapps, imidlalo, nakweyiphi na enye inkqubo yentengiso.

Thumela isicelo se POST ku /api/v1/tts/ ngegama lemodeli ne ID yesandi. Bona iphepha lethu le-API Documentation ngemizekelo yekhowudi kwi-Python, JavaScript, Go, kunye ne-cURL.

Ewe, nqakraza iqhosha lokudlala kweli phepha ukuva isampuli. Ungabhala umbhalo oqhelekileyo kwiphepha lombhalo ukuya kukuthetha kwaye wenze ukujonga kuqala simahla ngelizwi elithile.

Zama Baker (Chinese) Ngoku

Bhala nawuphi na umbhalo uze uyiva ithetha ngu Baker (Chinese). Ifumaneka simahla akukho phawu lufunekayo.