search

mpc001 / auto_avsr

Auto-AVSR: Lip-Reading Sentences Project
Apache License 2.0
158 stars 40 forks source link

Question about training on a Chinese dataset created by myself. #31

Closed liu33333 closed 4 months ago

liu33333 commented 4 months ago

As your following guidence say: image I’m prepareing the .csv file. But I don't understand the last step. The 'tokenize' method's output is a tensor. Should I transform the tensor to a list or use the tensor itself to create the .csv? Thanks for your help.