A basic question: Is there an up to date notebook that explain step by step how to generate speech from text using the pre-trained models?
I have tried a few that I have found on the site but I end up finding code has changed, etc. For example, I just tried this one…
…but load_config is not anymore on TTS.utils.generic_utils, setup_model from TTS.utils.generic_utils requires c parameter.
I am new to TTS, coming from Pytorch NLP, so most likely I am missing things. An introductory Notebook would be great.