Search papers, labs, and topics across Lattice.
3
0
4
3
Factorized neural codec representations can achieve low-latency speech generation without sacrificing reconstruction quality.
CPT+SFT may lead to the best performance in multiple-choice QA, but SFT alone is often a surprisingly effective and economical choice.
LLMs can judge speech recognition quality with near-human accuracy, blowing away traditional metrics like Word Error Rate.
