{"url":"/dataset/sonar-1","name":"SONAR","full_name":null,"description_markdown":"**SONAR**, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders. It substantially outperforms existing sentence embeddings such as LASER3 and LabSE on the xsim and xsim++ multilingual similarity search tasks.","description_withheld":null,"homepage":"https://github.com/facebookresearch/sonar","introduced_date":"2023-08-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/sentence-level-multimodal-and-language","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations","first_author":"Paul-Ambroise Duquenne","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://github.com/facebookresearch/SONAR/blob/main/LICENSE.md"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":["SONAR"],"data_loaders":[],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}