A Keras implementation of Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention based on the following projects:
https://github.com/Kyubyong/dc_tts
https://github.com/tugstugi/pytorch-dc-tts
My goals are to learn the deep neural networks and to experiment with training and synthesizing Kazakh language Text-To-Speech. Used 1h:25m single speaker dataset.
Demo on youtube:
