astorfi / 3D-convolutional-speaker-recognition

:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification
Apache License 2.0
781 stars 275 forks source link

can't create enrollment hdf5 file #5

Closed liveinnet closed 6 years ago

liveinnet commented 6 years ago

Hi astorfi: i try to run the program but i can't find a python script to create enrollment hdf5 file in code folder only exist create development hdf5 python script. how to create enrollment hdf5 file?

Mark

astorfi commented 6 years ago

@liveinnet Thanks for spending time. Creating development hdf5 is an example for showcasing how to do the task. Creating enrollment and etc can be similar to that and is dataset-based. Basically, the enrollment part is created similar to development phase with the difference of the identity of the speaker. The speaker subjects are disjoint in development and enrollment phases.