{"url":"/dataset/banglish","name":"Banglish","full_name":null,"description_markdown":"A Bilingual Dataset for Bangla and English Voice Commands\r\n\r\nColloquial Bangla has adopted many English words due to colonial influence. In conversational Bangla, it is quite common to speak in a mixture of English and Bangla. This phenomenon, prevalent in conversational language is known as code-switching (CS). CS is defined as the continuous alternation between two languages in a single conversation. Thus, in Bangla natural language processing, it is often necessary to map a single base command to its many different variants - spoken in multiple mixtures of English and Bangla. In order to facilitate this, we have curated a dataset centered around common browser commands.","description_withheld":null,"homepage":"https://github.com/space-urchin/CSVC-Net/tree/main/dataset","introduced_date":"2021-08-17","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Voice Query Recognition","url":"/task/voice-query-recognition","datasets_with_task":"/datasets/task/voice-query-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Bengali","url":"/datasets/language/bengali"}],"variants":["Banglish"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/voice-query-recognition-on-banglish","task":"Voice Query Recognition","dataset_variant":"Banglish","rows":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"CSVC-Net","paper":"/paper/csvc-net-code-switched-voice-command","metrics":{"Accuracy (%)":"92.08"},"code_links":[{"title":"space-urchin/CSVC-Net","url":"https://github.com/space-urchin/CSVC-Net"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/csvc-net-code-switched-voice-command","title":"CSVC-Net: Code-Switched Voice Command Classification using Deep CNN-LSTM Network","date":"2021-08-17","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}