Open psparulsharma opened 7 years ago
@psparulsharma hello, it is because that librispeech is very large, to avoid loading so large dataset once, i split them into several small datasets. and running every directory is based on the pretrained model.
Looking into the code the model initializes the tf.session() for every subdirectory (4000 samples). It doesn't make sense (at least to me). Also there is no relation for the model of each of the subdirectories. I am referring to ./Automatic_Speech_Recognition/main/libri_train.py file. Please explain.