keonlee9420/Comprehensive-E2E-TTS
A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS
Python
Issues
- 2
multi GPU training doesnt seem to work
#6 opened by ppisljar - 9
severe metallic sound
#3 opened by GuangChen2016 - 0
any demo voice result?
#5 opened by lucasjinreal - 0
- 2
Variance Loss RuntimeError
#2 opened by roedoejet