{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","arxiv_id":"2303.17395","date":"2023-03-30","proceeding":null,"authors":["Xinhao Mei","Chutong Meng","Haohe Liu","Qiuqiang Kong","Tom Ko","Chengqi Zhao","Mark D. Plumbley","Yuexian Zou","Wenwu Wang"],"abstract":"The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited in size. To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. We sourced audio clips and their raw descriptions from web sources and a sound event detection dataset. However, the online-harvested raw descriptions are highly noisy and unsuitable for direct use in tasks such as automated audio captioning. To overcome this issue, we propose a three-stage processing pipeline for filtering noisy data and generating high-quality captions, where ChatGPT, a large language model, is leveraged to filter and transform raw descriptions automatically. We conduct a comprehensive analysis of the characteristics of WavCaps dataset and evaluate it on multiple downstream audio-language multimodal learning tasks. The systems trained on WavCaps outperform previous state-of-the-art (SOTA) models by a significant margin. Our aspiration is for the WavCaps dataset we have proposed to facilitate research in audio-language multimodal learning and demonstrate the potential of utilizing ChatGPT to enhance academic research. Our dataset and codes are available at https://github.com/XinhaoMei/WavCaps.","url_abs":"https://arxiv.org/abs/2303.17395v2","url_pdf":"https://arxiv.org/pdf/2303.17395v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"wavcaps-a-chatgpt-assisted-weakly-labelled","repo_url":"https://github.com/xinhaomei/wavcaps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wavcaps-a-chatgpt-assisted-weakly-labelled","repo_url":"https://github.com/gzhu06/cacophony","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"wavcaps-a-chatgpt-assisted-weakly-labelled","repo_url":"https://github.com/labbeti/aac-datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"},{"task_slug":"zero-shot-environment-sound-classification","task_name":"Zero-Shot Environment Sound Classification"},{"task_slug":"zero-shot-audio-classification","task_name":"Zero-shot Audio Classification"},{"task_slug":"zero-shot-text-to-audio-retrieval","task_name":"Zero-shot Text to Audio Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"wavcaps","name":"WavCaps","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.17395","atlas_url":"https://app.syntology.ai/?focus=2303.17395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17395"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/labbeti/aac-datasets","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xinhaomei/wavcaps","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gzhu06/cacophony","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":3},"by_repo_kind":{"listed":{"samples":12,"ran":9,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"619e138b6c356681","entry":"ast_update_pretrained_parameters","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/audio_models/mae.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/audio_models/mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"619e138b6c356681"}},{"code_sha256_prefix":"935ad642c14e60f5","entry":"count_params","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/load_model.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/load_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"935ad642c14e60f5"}},{"code_sha256_prefix":"12a1bb1ff6ec7d06","entry":"create_position_ids_from_input_ids","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/text_models/roberta_text_model.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/text_models/roberta_text_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12a1bb1ff6ec7d06"}},{"code_sha256_prefix":"558e8d8554f2f975","entry":"get_audioset_mapping_cache_path","repo":"labbeti/aac-datasets","repo_kind":"listed","path":"src/aac_datasets/utils/audioset_mapping.py","file_url":"https://github.com/labbeti/aac-datasets/blob/HEAD/src/aac_datasets/utils/audioset_mapping.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"558e8d8554f2f975"}},{"code_sha256_prefix":"8ac516f37a509ac9","entry":"get_sin_cos_pos_embed","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/audio_models/mae.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/audio_models/mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ac516f37a509ac9"}},{"code_sha256_prefix":"ca913bee7808fbc3","entry":"load_audioset_mapping","repo":"labbeti/aac-datasets","repo_kind":"listed","path":"src/aac_datasets/utils/audioset_mapping.py","file_url":"https://github.com/labbeti/aac-datasets/blob/HEAD/src/aac_datasets/utils/audioset_mapping.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca913bee7808fbc3"}},{"code_sha256_prefix":"c1f4b5c3e3948f5f","entry":"load_audioset_name_to_idx","repo":"labbeti/aac-datasets","repo_kind":"listed","path":"src/aac_datasets/utils/audioset_mapping.py","file_url":"https://github.com/labbeti/aac-datasets/blob/HEAD/src/aac_datasets/utils/audioset_mapping.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1f4b5c3e3948f5f"}},{"code_sha256_prefix":"0068a7c10ff0707d","entry":"roberta_update_pretrained_parameters","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/text_models/roberta_text_model.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/text_models/roberta_text_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0068a7c10ff0707d"}},{"code_sha256_prefix":"93d588113f6aff52","entry":"spectrogram_to_patches","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/eval/eval_caco_torch.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/eval/eval_caco_torch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93d588113f6aff52"}},{"code_sha256_prefix":"131ab70b285d350e","entry":"decode","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/caco.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/caco.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"131ab70b285d350e"}},{"code_sha256_prefix":"1144ea63154654a4","entry":"load_audiomae","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/load_model.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/load_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1144ea63154654a4"}},{"code_sha256_prefix":"062ce739f0119f15","entry":"load_caco","repo":"gzhu06/cacophony","repo_kind":"listed","path":"src/caco/load_model.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/load_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"062ce739f0119f15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}