Beam College 2023 | Part 2: Beam python conventions, overall pipeline structure, datasets

Explore how to choose the right ML models for your Beam pipeline. This session covers choosing a model, and using the ModelHandler classes to adapt that model to a Beam pipeline transform. As an example, we show how to use a text LLM from HuggingFace.
Our example pipeline for this exercise takes voice input, turns it into text, classifies the text based on use case, sends each class to a different model, and turns the text output back into a voice sample.