Christian Fuegen

AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs

2023 · arXiv (Cornell University)

In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of original LLM capabilities, without using any carefully curated paired data. The resulting …

Libri-Light: A Benchmark for ASR with Limited or No Supervision

2020

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K …