VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
SSML-i siltidesse teksti segamine täpseks kontrollimiseks:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Sildid valitud mudelil mõistavad ~ klõpsa ühe kukutamiseks teksti, kus see juhtub:
See mudel loeb lihtsat teksti, nii et sisemisi silte ignoreeritakse. Sildil põhinevate emotsioonide puhul lülituge ekspressiivsele mudelile nagu Orpheus või Bark.
Kohandatud häälduste määramine (sõna = hääldus):
Info 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.
Parim: General-purpose text-to-speech with natural prosody
Kõigi sirvimine VITS hääledPõgusalt
- Arendaja
- Jaehyeon Kim et al.
- Litsents
- MIT
- Määramistasand
- free
- Kiirus
- fast
- Hääle kloonimine
- Ei.
- Keeled
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Maks. märgid
- 2000