We have made quite a lot of progress since our last post. After an intense period of training and experimenting, we decided that we would use a LJspeech pre-trained Waveglow and focus on our Tacotron2 performance. Background In our previous blogs we focused a lot of our efforts on getting our models to converge. We … Continue reading Text to Speech Modeling on Youtube Sourced Single Speaker Data Set with Tacotron2 and Waveglow: Part 3
read More