ChatPaper.aiChatPaper

Slamming: Training a Speech Language Model on One GPU in a Day

February 19, 2025
Authors: Gallil Maimon, Avishai Elmakies, Yossi Adi
cs.AI

Abstract

We introduce Slam, a recipe for training high-quality Speech Language Models (SLMs) on a single academic GPU in 24 hours. We do so through empirical analysis of model initialisation and architecture, synthetic training data, preference optimisation with synthetic data and tweaking all other components. We empirically demonstrate that this training recipe also scales well with more compute getting results on par with leading SLMs in a fraction of the compute cost. We hope these insights will make SLM training and research more accessible. In the context of SLM scaling laws, our results far outperform predicted compute optimal performance, giving an optimistic view to SLM feasibility. See code, data, models, samples at - https://pages.cs.huji.ac.il/adiyoss-lab/slamming .

Summary

AI-Generated Summary

PDF662February 25, 2025