search

b04901014 / UUVC

Official implementation for the paper: A Unified One-Shot Prosody and Speaker Conversion System with Self-Supervised Discrete Speech Units.
MIT License
73 stars 9 forks source link

About trainining details #10

Closed yvetteteng closed 1 year ago

yvetteteng commented 1 year ago

Hello! I want to know more details about experiment setup like device and time you used. How long does it take to train the entire model ? I train this full model on ESD dataset and use 1 v100. I found that it cost about 1 hour for 200 iterations. I wonder if there is any problem I met.