VITS ТТС
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Тодорхой хяналтын тулд SSML тэмдгээр текстээ буулгах:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Бүх
Энэ загвар нь энгийн утга уншдаг, тиймээс доторх тэмдгийг үл тоомсорлодог. Тэг- суурилсан сэтгэл хөдлөл, Orpheus эсвэл Bark- шиг илэрхийлэх загвар руу шилжинэ.
Өөрийн дуудлагыг тодорхойлох (үг = дуудлага):
Тодорхойлолт VITS
VITS — Variational Inference with adversarial learning for end-to-end Text-to-Speech — was introduced by Jaehyeon Kim and collaborators in 2021 and became a foundational architecture for modern neural speech. Rather than the older two-stage pipeline, it synthesizes audio in a single parallel end-to-end pass, pairing a variational autoencoder with normalizing flows and a GAN-style adversarial training process to lift naturalness. At about 25M parameters and trained on ~585 hours, it produces natural prosody at fast inference speeds and supports multiple speakers. It serves as a solid general-purpose, free baseline and underpins many later models such as Piper and MeloTTS.
Хамгийн сайн: General-purpose text-to-speech with natural prosody
Бүхнийг харах VITS дуунуудНүүр хуудас
- Хөгжүүлэгч
- Jaehyeon Kim et al.
- Лиценз
- MIT
- Үхрийн
- free
- Хурд
- fast
- Дууны дугуй
- Үгүй
- Хэл
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Хамгийн их үсэг
- 2000