Search papers, labs, and topics across Lattice.
Meta AI
3
0
5
6
Jointly training a speech encoder and language model on mel-spectrograms not only boosts zero-shot speech translation, but also fixes annoying speech synthesis quirks like endless silences.
Forget scaling laws: a specialized 8B parameter translation model can outperform a 70B general-purpose LLM on 1,600 languages.
OmniSONAR halves cross-lingual search error on FLORES and reduces error by 15x on BIBLE, proving that truly universal sentence embeddings across thousands of languages and modalities are now within reach.
