“Jukebox Sample Explorer”, 2020-04-30 (; backlinks; similar):
A large dataset of 7131 musical songs generated by OpenAI’s Jukebox neural network.
The dataset is classified & searchable by model (including samples generated by models early in training & of low quality), type of song (the model continuing an existing piece of music, generating in the style of a specific artist, given brand-new lyrics, no lyrics at all), genre (hip hop/jazz/country/rock/pop/metal/etc), artist (everyone from Elton John to Rage to Eagles), and sampling temperature (top-k, governing tradeoff between randomness and predictability).