{"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/pengi-an-audio-language-model-for-audio-tasks-1","title":"Pengi: An Audio Language Model for Audio Tasks","arxiv_id":"2305.11834","date":"2023-05-19","proceeding":"NeurIPS 2023 11","authors":["Soham Deshmukh","Benjamin Elizalde","Rita Singh","Huaming Wang"],"abstract":"In the domain of audio processing, Transfer Learning has facilitated the rise of Self-Supervised Learning and Zero-Shot Learning techniques. These approaches have led to the development of versatile models capable of tackling a wide array of tasks, while delivering state-of-the-art performance. However, current models inherently lack the capacity to produce the requisite language for open-ended tasks, such as Audio Captioning or Audio Question & Answering. We introduce Pengi, a novel Audio Language Model that leverages Transfer Learning by framing all audio tasks as text-generation tasks. It takes as input, an audio recording, and text, and generates free-form text as output. The input audio is represented as a sequence of continuous embeddings by an audio encoder. A text encoder does the same for the corresponding text input. Both sequences are combined as a prefix to prompt a pre-trained frozen language model. The unified architecture of Pengi enables open-ended tasks and close-ended tasks without any additional fine-tuning or task-specific extensions. When evaluated on 22 downstream tasks, our approach yields state-of-the-art performance in several of them. Our results show that connecting language models with audio models is a major step towards general-purpose audio understanding","url_abs":"https://arxiv.org/abs/2305.11834v2","url_pdf":"https://arxiv.org/pdf/2305.11834v2.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":"pengi-an-audio-language-model-for-audio-tasks-1","repo_url":"https://github.com/microsoft/pengi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-question-answering","task_name":"Audio Question Answering"},{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11834","atlas_url":"https://app.syntology.ai/?focus=2305.11834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11834"}},"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/microsoft/pengi","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"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":"5337e68cdb46397d","entry":"do_mixup","repo":"microsoft/pengi","repo_kind":"official","path":"models/htsat.py","file_url":"https://github.com/microsoft/pengi/blob/HEAD/models/htsat.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5337e68cdb46397d"}},{"code_sha256_prefix":"3ac6b7d76e8e3584","entry":"drop_path","repo":"microsoft/pengi","repo_kind":"official","path":"models/htsat.py","file_url":"https://github.com/microsoft/pengi/blob/HEAD/models/htsat.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"code_sha256_prefix":"bdcac6c19196f655","entry":"interpolate","repo":"microsoft/pengi","repo_kind":"official","path":"models/htsat.py","file_url":"https://github.com/microsoft/pengi/blob/HEAD/models/htsat.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdcac6c19196f655"}},{"code_sha256_prefix":"360a191dd28ceec7","entry":"get_decoder","repo":"microsoft/pengi","repo_kind":"official","path":"models/decoder.py","file_url":"https://github.com/microsoft/pengi/blob/HEAD/models/decoder.py","link_basis":"plan_row","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":"360a191dd28ceec7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}