robmsmt / KerasDeepSpeech

A Keras CTC implementation of Baidu's DeepSpeech for model experimentation
GNU Affero General Public License v3.0
242 stars 79 forks source link

ZeroPadding1D at the ds2_gru_model #7

Open Edresson opened 6 years ago

Edresson commented 6 years ago

Hi, I don't understand, because you use ZeroPadding1D in this model. you are adding 2048 zeros in the second shape dimension. example: when input shape is: (1,280,161) after pass in the ZeroPadding1D layer the output is (1,2328,161).

Do you want to keep the sequence fixed in 2048? if yes, is it necessary to calculate the number of zeros required for each of the inputs?

Thank you for your response.