This code is based on NVIDIA implementation of Tacotron2 and Waveglow. It is shaved to reduce dependencies and simplify code
https://github.com/NVIDIA/tacotron2 https://github.com/NVIDIA/waveglow
For realtime synthesis it requires GPU card like GTX 1080 or RTX 2080
Download model here ~900Mb
http://alphacephei.com/tts/tacotron-models.tar.gz
Unpack them into folder tacotron-models here.
Unpack models to models folder and run test.py, it will create the audio file test.wav