search

rendchevi / nix-tts

🐤 Nix-TTS: Lightweight and End-to-end Text-to-Speech via Module-wise Distillation
MIT License
243 stars 33 forks source link

Discussion: How about distil MAS result from teacher VITS to replace the Text Aligner? #10

Open TinaChen95 opened 2 years ago

TinaChen95 commented 2 years ago

I found that VITS's MAS result is very accurate, so why not distil the duration information to train the student model?