VITS

Baker (Chinese)

_Nkebi Chinese Neutral VITS

Baker (Chinese) bụ olu neutral AI nke ejiri ike site na móòdù ngwe-ka-asụsụ VITS. Asụsụ free-tier a na-ekwu Chinese ma na-enye nsụgharị okwu Ọfụụ-ọdịmma. Na n'ụdị nrụpụta ọsọ nke N'ime nkeji nakwa nkwalite nke 3/5, Baker (Chinese) dịkwa mma maka general-purpose text-to-speech with natural prosody. Ékèkọ́rá VITS engine site na Jaehyeon Kim et al. under the MIT license, na-eme ka ọ bụrụ nke dị mma maka ojiji azụmahịa. Nhazi ndị dị mkpa gụnyere: end-to-end synthesis, natural prosody, fast inference, multiple speakers.

Enweghị ụghasị

VITSNdesịta ozi model

Móòdù VITS
Debanye aha Jaehyeon Kim et al.
Nhazi
Nhazi Nnọọ
Ikikere MIT
Ọrụ Enweghị ike ịhụ ya
Ụdị Free (enweghị akara a na-eji)
Paramita 25M
Nhazi VAE + Normalizing Flows + GAN
Ndesịta ozi ndịna 585 awa
Ụbọchị 2021

Ọrụ kacha mma maka Baker (Chinese)

Usoroiheomume a na-atụ aro site na ụda a

Agụgụala na ndezi

Jiri Baker (Chinese) ka ịkọwapụta ihenhọrọ nke ogologo-fomu na n'ụzọ na-ezighị ezi nakwa nkọwa.

Vidéọ̀wù

Tinye nkọwa profaịlụ na vidiyo YouTube, mgbasaozi, na ihenhọrọ mgbasaozi mmekọrịta.

Usoroiheomume na ntọala

Nhazi nke n'ụzọ nkịtị na-eme ka ụda a dị mma maka usoroiheomume oge-ọdịnihu, ndị na-agụ ihuenyo, nakwa ngwaọrụ nlebara anya.

E-Lerinụ na Ọzụzụ

Kewapụta ihe ndị na-akụzi, kọleji, na ihe ọmụmụ na-akọwapụta AI.

Ndị ọzọ VITS Ụda

Ụda ndị ọzọ site na móòdù TTS ahụ

Default

English Neutral

Ajụjụ ndị a na-ajụkarị

VITS (Variational Inference na-amụ ihe na-abịanụ maka ngwụcha-na-abịanụ Text-to-Speech) bụ ụzọ TTS na-abịanụ na-abịanụ nke na-emepụta ụda dị mma karịa ụdị abụọ nke ugbu a. Ọ na-ahọrọ ntụgharị dị iche iche na-agbakwunye na ntụgharị na usoro nkuzi na-abịanụ, na-enwetakwa mmelite dị mkpa na nghọta.

VITS a rụpụtara site na Jaehyeon Kim na ndị ọzọ. na a hapụla ya n'okpuru MIT license, nke na-enye ikike iji ya maka ọrụ ọha na eze nke ụda a rụpụtara.

VITS na-akwado asụsụ 4: English, Chinese, Japanese, Korean.

VITS bụ na Free tier - free - enweghị kredit dị mkpa. I nwere ike ịhụ n'ihu ọbụla VITS ụda n'efu tupu ịmepụta ụda zuru ezu.

VITS has very fast generation speed. It runs in near real-time, making it suitable for streaming and interactive applications.

VITS a raara 3/5 maka ụda n'ọdịnaya na TTS.ai. O na-enye ụda dị mma dịkwa mma maka ọtụtụ usoroiheomume.

Ee, VITS na-eji setịpụrụ ụda ndị ahụ. Maka ịkọsa ụda, jiri móòdù dị ka CosyVoice 2, GPT-SoVITS, mọọbụ Chatterbox.

Ee, VITS a na-atụ aro ya maka ngwe-na-asụsụ nke a na-ejikarị eme ihe na-enweghị n'aka. Nhazi ya nke n'aka, n'aka nke n'aka, ike ịkọwapụta nke n'ụzọ nkịtị na-eme ka ọ bụrụ nhọrọ dị mma maka ihenhọrọ a.

Ee, VITS bụ na-enye ikike n'okpuru MIT, nke na-enye ohere iji ya maka ọrụ azụmahịa. Oyi a haziri na VITS ụda nwere ike iji ya na vidio, podcasts, ngwaike, egwuregwu, nakwa ihe ọbụla ọzọ maka ọrụ azụmahịa.

Ee, ụda niile na TTS.ai na-eji ụdị ndị a na-enye ikike n'ụzọ azụmahịa (MIT, Apache 2.0). Ọdịdị a haziri bụ nke gị iji jiri ya na vidio, podcasts, ngwa, egwuregwu, nakwa usoroiheomume ọbụla ọzọ na-enye ikike n'ụzọ azụmahịa.

Ziga arịrịọ POST na /api/v1/tts/ na aha móòdù nakwa ID ụda. Gụọ ibe anyị nke Dọkumenti API maka ihenhọrọ koodị na Python, JavaScript, Go, nakwa cURL.

Ee, pịa bọtịn egwu na ihuakwụkwọ a ka ịgụnye nlele. I nwere ike ịgụnye ngwe emeredịkachọrọ na ihuakwụkwọ ngwe ka ọsụsọ ma mepụta nlele n'efu na ụda ọbụla.

Chọ̀ọ́ Baker (Chinese) Ugbu a

Tinye ngwe ọbụla ma gụọ ya site na Baker (Chinese). N'efu iji na-enweghị ihenhọrọ ndị ahụ achọrọ.