Unleashing Speech Intelligence through DSLMs // Andrew Seagraves // LLMs in Prod Con Lightning Talk

// Abstract
Despite their advanced capabilities, Language Model Models (LLMs) are often too slow and resource-intensive for use at scale in voice applications, particularly for large-scale audio or low-latency real-time processing. SlimFast addresses this challenge by introducing Domain Specific Language Models (DSLMs) that are distilled from LLMs on specific data domains and tasks. SlimFast provides a practical solution for real-world applications, offering blazingly fast and resource-conscious models while maintaining high performance on speech intelligence tasks. We demo a new ASR-DSLM …

abstract advanced andrew applications audio challenge intelligence language language model language models latency llms low processing prod real-time scale speech talk through voice voice applications