MuseNet is a deep neural network created by OpenAI that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. It uses the same general-purpose unsupervised technology as GPT-2, a large-scale transformer model trained to predict the next token in a sequence, whether audio or text. The model is trained on data from MIDI files and can generate samples in a chosen style by starting with a prompt. It uses several embeddings such as positional embeddings, a timing embedding, and structural embeddings to give the model more context.
