Jul 2026
An Omnilingual-ASR-Based Speech-LLM System for the 2nd MLC-SLM Challenge
A cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, CAM++ embedding-based two-speaker clustering, and a LoRA-adapted omniASR LLM 7B v2 recognizer, with no oracle segmentation or speaker labels at test time is described.
Shuming Fang, Shuifei Zeng
· arXiv.org · 0 citations