Hacker News Reader

The first demo on that page was trained from a 32kbps crappy sound quality clip of winston churchill...?

garbage in, garbage out?

Must have been, it sounds very much like the quality of the "we shall fight on the beaches" speech.

A bit unfortunate choice for a demo, sadly.

Good point, thanks. And I was thinking it will show that the model can really synthesize very varied samples... ;)

It does, but maybe put it last!

Did exactly that, thanks for spotting that. :)