VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Za natančen nadzor zavijte svoje besedilo v oznake SSML:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Oznake izbranega modela razume – kliknite, da spustite enega v svoje besedilo, kjer se zgodi:
Ta model bere navadno besedilo, zato se v vrstici ignorirajo. Za čustva, ki temeljijo na tag, preklopite na izražen model, kot je Orfeus ali Bark.
Opredelitev posebnih izgovorov (beseda = izgovor):
O projektu 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.
Najboljše za: General-purpose text-to-speech with natural prosody
Brskaj vse VITS glasoviNa pogled
- Razvijalec
- Jaehyeon Kim et al.
- Licenca
- MIT
- Stopnja
- free
- Hitrost
- fast
- kloniranje glasu
- Ne
- Jeziki
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Največ znakov
- 2000