Slamming: Training a Speech Language Model on One GPU in a Day
This makes SLM training and research more accessible, especially for academic settings with limited compute, though it is incremental in optimizing existing methods.
The paper tackles the problem of training high-quality Speech Language Models (SLMs) with limited computational resources, achieving results on par with leading SLMs in a fraction of the compute cost by using a recipe that enables training on a single GPU in 24 hours.
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 .