francoisgermain / SpeechDenoisingWithDeepFeatureLosses

Speech Denoising with Deep Feature Losses
MIT License
183 stars 53 forks source link

Number of epochs for pretrained #4

Open reddyanilkumar opened 5 years ago

reddyanilkumar commented 5 years ago

Could you please let me know the number of epochs the pre-trained model is trained.

saurabh-kataria commented 5 years ago

Since there are two models involved (speech enhancement network and the feature loss network), it would be good to know the number of epochs for both of them?

francoisgermain commented 5 years ago

The number of epochs for the training should correspond to the hard-coded one in the given scripts (i.e., 2500 epochs for loss network, 310 for speech enhancement network).