Bark – GPT-style realistic multilingual text-to-speech generation

Re:Bark – GPT-style realistic multilingual text-to-speech ge... by rck on Thursday April 20, 2023 @02:35PM (#35644234)

Any idea what the training data for this is? Looking at the model, it looks like it is literally just copy-paste from Karpathy's nanoGPT, so the training data is what's most interesting. Pretty amazing anyway.

[ Parent | on HN ]

Re:Bark – GPT-style realistic multilingual text-to-speech ge... by unraveller on Thursday April 20, 2023 @02:50PM (#35644453)

I found a secret demo page that shows in real time how they assess any sound file's mood swings along with number of detected laughs, coughs, etc. Guessing that ability is involved somehow.

[ Parent | on HN ]

Re:Bark – GPT-style realistic multilingual text-to-speech ge... by gkucsko on Thursday April 20, 2023 @03:30PM (#35645025)

haha https://demo.suno.ai

[ Parent | on HN ]