{"url":"/dataset/tie","name":"TIE","full_name":"https://github.com/raianand1991/TIE","description_markdown":"Click to add a brief description of the dataset (Markdown and LaTeX enabled).\r\nThe TIE(Technical Indian English) dataset is a massive speech dataset of ~750 GB, consisting of ~9.8K technical lectures in English, along with their transcripts. The lectures were delivered by instructors from all over India and were sourced from the NPTEL website","description_withheld":null,"homepage":"","introduced_date":"2023-07-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-deep-dive-into-the-disparity-of-word-error","title":"A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos","first_author":"Anand Kumar Rai","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["TIE"],"data_loaders":[],"num_papers_in_archive":2,"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."}