24 au 26 février, 2027
Montréal, Canada
A Practical Guide to Multilingual Speech-to-Text and LLMs
Working with natural language has always been complex. LLMs have made it more accessible, but production applications still face significant challenges, especially when dealing with multiple languages. This talk covers common pitfalls in multilingual audio and text workflows, along with practical approaches for selecting, evaluating, and combining speech-to-text and language models.
Jack Tacchi
Osedea
Jack is a Senior AI Developer at Osedea. With over 10 years of experience and a PhD in Data Science, he has worked professionally in numerous areas of AI, including computer vision, natural language processing, large language models, and agentic solutions. In his spare time he likes to code more experimental projects, including a 3D simulation using an evolutionary algorithm.
