Do we have to write code for preprocessing the dataset?

astorfi / lip-reading-deeplearning

:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

Apache License 2.0

1.84k stars 321 forks source link

Do we have to write code for preprocessing the dataset? #31

Closed ashish-roopan closed 4 years ago

ashish-roopan commented 4 years ago

I cant find any info on the repo about preprocessing the input data before training. Can you please say which dataset to use and how to train the model with that dataset?

astorfi commented 4 years ago

Please check https://github.com/astorfi/lip-reading-deeplearning/blob/master/code/speech-input/input_feature.py and the paper for further details.