how to generate a real tts

ttsunion / Deep-Expression

An Attention Based Open-Source End to End Speech Synthesis Framework, No CNN, No RNN, No MFCC!!!

86 stars 27 forks source link

how to generate a real tts #5

Open alain2208 opened 6 years ago

alain2208 commented 6 years ago

Hi currently your scripts re generate the original wav. I did not find the way to do a text to speech based on a random phrase different from the original one. Maybe still not implemented?

FonzieTree commented 6 years ago

Hi, @alain2208, thank you for your comment. I think your issue is the same to isssue 4, please visit https://github.com/ttsunion/Deep-Expression/issues/4.

alain2208 commented 6 years ago

yes it seems the same thanks

surenreddy commented 6 years ago

Why is "y:wav" is required as input for inference?

Is it possible to generate audio for new labels(batch_size=4) that are not in the training set? In that case what should be "y:wav" ?