DataHour: Text to Sound - Train Your Large Language Models

Dive into the realm of innovation with our captivating DataHour: "Text to Sound - Train Your Large Language Models." In this session, we delve deep into the process of crafting your own Large Language Models (LLMs) specifically designed for "Musician's Intent Recognition" within the fascinating domain of "Text to Sound" in Generative AI Guitar Sounds.

The speaker brings a wealth of expertise to the forefront, drawing insights from her pivotal role as the Lead Research Coordinator of the Text to Sound Team in the groundbreaking "The Sound of AI" Open Source Research Project. Through detailed discussions and real-world examples, she will guide you through the intricate steps of training Large Language Models that excel in understanding and translating musicians' intentions into captivating guitar sounds.

Dr Ruby Annette is a researcher, open-source project team lead and machine learning engineer with experience in academic R&D and the software industry. She has a PhD and a master's degree in Information Technology. Dr Ruby is actively involved in developing patentable solutions for AIOps (Artificial Intelligence for IT Operations) as a machine learning engineer in Texas, USA. Her expertise is in fine-tuning the NLP and Deep Learning models to high accuracy for real-time deployment. In her career, Dr Ruby has worked on applying NLP & Deep learning for AIOps / Cloud Intelligence, Recommender Systems, and Music Generation. She has authored more than 14 papers and has published two patents.