Rajath Kumar

@mab85 just change the dimensions in the code wrt to your dataset

@amitmanchanda1995 I was predicting the output after each epoch, so I had compiled it, it is not necessary if you are not interested in seeing the generator output after each...

@amitmanchanda1995 Ahh, I remember now, check line 151. I could have simply reduced the lr of dcgan, but I have done it separately, to call the optimiser function I needed...

@YichiHuang The data is from Librispeech, and those are the keywords that I trained my models on, this code is for Text Dependent Speaker Verification

@YichiHuang Yes, used Kaldi ASR to do so

The data is open source, search for LibriSpeech, it is a 1000 hour dataset

@drivenow It's this http://www.cs.cmu.edu/~chanwook/MySoftware/rm1_Spk-by-Spk_MLLR/rm1_PNCC_MLLR_1/rm1/python/sphinx/htkmfc.py

@selimelawwa Speaker ID's are provided in the dataset