We've sent a verification link by email
Didn't receive the email? Check your Spam folder, it may have been caught by a filter. If you still don't see it, you can resend the verification email.
These were all created by Andrej Karpathy's char-rnn by the following procedure:
* convert training audio to mono 22kHz 8 bit wav
* train standard char-rnn
* read a chunk of priming audio, prime the trained net and then keep sampling for several K steps
Training data used were Mike Will's "Drinks on us" and Farmersmanual's explorers_we. Samples were created using network snapshots from all phases of training.
Network size, number of layers, epoch and loss are encoded in the filename.