News for hackers. Stuff that matters.
Re:Tacotron 2: Generating Human-Like Speech from Text by sixdimensional on Wednesday December 20, 2017 @12:25AM (#15967219)
I've been wondering lately, it seems like audio books might be an amazing training resource for models like these, if you could get the script that the reader was working from!
Re:Tacotron 2: Generating Human-Like Speech from Text by sdenton4 on Wednesday December 20, 2017 @02:17AM (#15967667)
Your wish, granted. http://www.openslr.org/12/

It's 1000 hours of audio book readings, segmented by sentence, with transcripts. All from project Gutenberg, so maybe a little bit heavy on Victorian bodice rippers and such, but certainly a great trove of training data...

Re:Tacotron 2: Generating Human-Like Speech from Text by j_s on Wednesday December 20, 2017 @07:11AM (#15968913)
Re:Tacotron 2: Generating Human-Like Speech from Text by woodson on Wednesday December 20, 2017 @10:54AM (#15970599)
That data is no good for this purpose, as it’s from a lot of different speakers and does not have speaker labels, i.e., you can’t tell which sentences were spoken by which speaker.