Search papers, labs, and topics across Lattice.
3
0
5
Fine-tuning a TTS model with LoRA can boost Khmer speech synthesis quality significantly, while revealing that adaptation may not benefit already well-supported languages like Korean.
Retriever choice is the real bottleneck in Khmer RAG, and no single generator model dominates across faithfulness, factual correctness, and answer relevance.
Forget fancy LLM-based approaches: simple character-based chunking beats them all for RAG in low-resource languages.
