rishikksh20
Can't I change the length of my voice length?
Hello, I tried to use a pretrained model with kss data, but a 1 second wav file was printed out. Can you only make a 1-second file with that model? If I want a 7-second voice file, which part should I modify? Thank you.
Hello, I tried to use a pretrained model with kss data, but a 1 second wav file was printed out. Can you only make a 1-second file with that model? If I want a 7-second voice file, which part should I modify? Thank you.
Hello, @Koeunseooooo ,
KSS dataset consists of 44,100 KHz sampling rate. When I train the VocGAN on KSS dataset, I downsampled the dataset to 22,050 KHz.
If you train your acoustic model such as FastSpeech2, Tacotron2 or etcs on different sampling rate(i.e., not 22,050 KHz samples), that might be problem. In this case, you can solve this problem using 2 ways: (1) train your acoustic model with 22,050 KHz samples or (2) train VocGAN using your custom dataset without any change of sampling rate.
Since this is not my own repository, I may rarely check your question. If you got any further question, please email me.
Thank you.
