Tacotron-2
Tacotron-2 copied to clipboard
How to use trained model for prediction?
Hi, I'm new to Tensorflow here and I want to start an assignment by implementing this project. My question is, how can I feed my text input into my pre-trained model to generate wav file output.
I know this question might be too obvious for most people here, but I really need help in this situation.
Thank.
Hi, I'm new to Tensorflow here and I want to start an assignment by implementing this project. My question is, how can I feed my text input into my pre-trained model to generate wav file output.
I know this question might be too obvious for most people here, but I really need help in this situation.
Thank.
if you want to get the result synthesized for the particular/custom text you need to provide the at line 62 of synthesize.py "parser.add_argument('--text_list', default='sentences.txt', help='Text file contains list of texts to be synthesized. Valid if mode=eval')" give default="sentence.txt" and save the your interested texts in the file sentences.txt which is saved in the current directory.
and run the synthesize.py.