search

MTG / WGANSing

Multi-voice singing voice synthesis
235 stars 44 forks source link

variable max_phr_len in config.py #21

Closed deblinbagchi closed 3 years ago

deblinbagchi commented 4 years ago

I am trying to use the GAN toolkit to generate read speech. I am currently trying to understand your code. It would really help if you tell me what is the role of the variable max_phr_len in config.py ? I see the value is set to 128. What would happen if I increase or decrease that value ? I have been reading your paper but can't seem to understand.

pc2752 commented 3 years ago

Hi, the variable max_phr_len in config refers to the maximum length of the input features (in time) used for training the network. It can be increased or decreased according to the dataset you have in ming, but you might also need to adjust the variable encoder_layers to account for the change in the length (eg: if you change the max_phr_len to 64, you could also decrease the encoder_layers to 6