{"url":"/dataset/speechinstruct","name":"SpeechInstruct","full_name":null,"description_markdown":"**SpeechInstruct** is a large-scale cross-modal speech instruction dataset. It contains 37,969 quadruplets composed of speech instructions, text instructions, text responses, and speech responses.\r\n\r\nSource: [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://arxiv.org/pdf/2305.11000v1.pdf)\r\n\r\nImage Source: [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://arxiv.org/pdf/2305.11000v1.pdf)","description_withheld":null,"homepage":"https://github.com/0nutation/SpeechGPT","introduced_date":"2023-05-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/speechgpt-empowering-large-language-models","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","first_author":"Dong Zhang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"}],"languages":[],"variants":["SpeechInstruct"],"data_loaders":[],"num_papers_in_archive":4,"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."}