VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Metini SSML taglarda dolap dogry kontrol üçin:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Saýlanan model aňlaýan taglar — birini metinde goýmak üçin basyň:
Bu model ýönekeý metin okaýar, şonuň üçin hatda taglar gözden düşürilýär. Tag-based emotions for, switch to an expression model like Orpheus or Bark.
Öz sözleriň terjimesini belli et (söz = terjime):
Habar 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.
Muňa iň gowy: General-purpose text-to-speech with natural prosody
Ehlini _Gözle VITS seslerBir seretseň
- Developer
- Jaehyeon Kim et al.
- Lisenziýa
- MIT
- _Göçür
- free
- Tizlik
- fast
- Ses klonlamak
- _Ýok
- Diller
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Maks. karakterler
- 2000