{"url":"/dataset/assamese-dataset","name":"assamese-dataset","full_name":"Assamese Dataset","description_markdown":"A collection of various NLP datasets in Assamese. These datasets are split into two: pre-training corpora and fine-tuning datasets.","description_withheld":null,"homepage":"https://github.com/indian-nlp/assamese-dataset","introduced_date":"2024-10-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/enhancing-assamese-nlp-capabilities","title":"Enhancing Assamese NLP Capabilities: Introducing a Centralized Dataset Repository","first_author":"S. Tamang","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["assamese-dataset"],"data_loaders":[],"num_papers_in_archive":1,"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."}