LoCoML: A Framework for Real-World ML Inference Pipelines
This work addresses the problem of managing heterogeneous ML model integration for stakeholders in collaborative, large-scale projects, offering a practical but incremental solution.
The paper tackles the challenge of integrating diverse machine learning models with varying architectures and data requirements in real-world applications, particularly for large-scale collaborative projects like the Bhashini Project, and shows that their low-code framework LoCoML adds minimal computational load while enabling efficient integration across over 20 languages.
The widespread adoption of machine learning (ML) has brought forth diverse models with varying architectures, and data requirements, introducing new challenges in integrating these systems into real-world applications. Traditional solutions often struggle to manage the complexities of connecting heterogeneous models, especially when dealing with varied technical specifications. These limitations are amplified in large-scale, collaborative projects where stakeholders contribute models with different technical specifications. To address these challenges, we developed LoCoML, a low-code framework designed to simplify the integration of diverse ML models within the context of the \textit{Bhashini Project} - a large-scale initiative aimed at integrating AI-driven language technologies such as automatic speech recognition, machine translation, text-to-speech, and optical character recognition to support seamless communication across more than 20 languages. Initial evaluations show that LoCoML adds only a small amount of computational load, making it efficient and effective for large-scale ML integration. Our practical insights show that a low-code approach can be a practical solution for connecting multiple ML models in a collaborative environment.