{"url":"/dataset/thchs-30","name":"THCHS-30","full_name":null,"description_markdown":"THCHS-30 is a free Chinese speech database\r\nTHCHS-30 that can be used to build a full-fledged\r\nChinese speech recognition system.\r\n\r\nSource: [THCHS-30 : A Free Chinese Speech Corpus](/paper/thchs-30-a-free-chinese-speech-corpus)","description_withheld":null,"homepage":"http://data.cslt.org/thchs30/README.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/thchs-30-a-free-chinese-speech-corpus","title":"THCHS-30 : A Free Chinese Speech Corpus","first_author":"Dong Wang","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"http://166.111.134.19:7777/data/thchs30/README.html"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["THCHS-30"],"data_loaders":[{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/hellodataset/THCHS-30","frameworks":["tf","pytorch"]}],"num_papers_in_archive":34,"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."}