VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Itzulbiratu zure testua SSML etiketetan kontrol zehatzagoa lortzeko:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Hautatutako modeloak ulertzen dituen etiketak — egin klik testuan jartzeko:
Eredu honek testu arrunta irakurtzen du, beraz, lerro-barneko etiketei ez zaie jaramonik egiten. Etiketetan oinarritutako emozioetarako, aldatu Orpheus edo Bark bezalako adierazpen-modelo batera.
Definitu ahoskera pertsonalizatuak (hitza = ahoskera):
Honi buruz 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.
Honako hauentzako onena: General-purpose text-to-speech with natural prosody
Arakatu dena VITS ahotsakBegirada batean
- Garatzailea
- Jaehyeon Kim et al.
- Lizentzia
- MIT
- Tier
- free
- Abiadura
- fast
- Ahots klonaketa
- Ez
- Hizkuntzak
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Gehienezko karaktereak
- 2000