Posted On: Feb 9, 2021

Today, we are excited to announce the launch of a new Transformer notebook on GitHub. AWS DeepComposer gives developers a creative way to get hands-on with the latest generative AI techniques expand their machine learning skills. The Transformer is a state-of-the-art model that works with sequential data such as genomic data or stock prices. By using a mechanism called attention, the algorithm attempts to learn the relationships between the different data points so it can generate better predictions. In the AWS DeepComposer Music studio, the Transformers feature will allow you to iteratively extend a melody to create new and longer compositions. Learn more about the Transformer technique in the learning capsule in the AWS DeepComposer Console.

The AWS DeepComposer Jupyter notebook contains code that shows how to train a custom Transformer-XL model with Amazon SageMaker. To get started, follow the instructions on the AWS DeepComposer GitHub page to create a notebook on the AWS DeepComposer GitHub page and read more about launching a Amazon SageMaker notebook instance.

Get hands-on with the AWS DeepComposer keyboard to start composing today. AWS DeepComposer keyboard is available for purchase on and is priced at $99. The pricing includes the keyboard and a 3-month free trial of AWS DeepComposer services.

Learn more about AWS DeepComposer.