{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.11834"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.11834"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.11834\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2305.11834"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.11834\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.11834"},"call":"get_concepts_for_paper(arxiv_id=\"2305.11834\")"}],"by_repo":[{"repo":"microsoft/pengi","kind":"official","samples":4,"ran":3,"instrument":2,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2305.11834.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2305.11834.svg"},"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_honours":1,"ran_fixture":2,"unverified":1},"n_samples":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":4,"ran":3,"n_ran_checked":1,"n_instrument":2,"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":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":1,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":2,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"5337e68cdb46397d","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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/2/float, mixup_lambda:Tensor/1/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5337e68cdb46397d"},"code_page":"/code/do-mixup","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5337e68cdb46397d"}},{"code_sha256":"3ac6b7d76e8e3584","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,"signature":"x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool","fixture_out_type":"Tensor","retrieve_with":{"tool":"get_code","code_sha256":"3ac6b7d76e8e3584"},"code_page":"/code/drop-path","census":{"url":"/census/drop-path","implementations":27,"papers":61,"distinct_outputs":5,"n_buckets":2,"bucket_key":[[2,"float","float32"]],"bucket_index":2,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-2","licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from fudan-zvg/SeaFormer, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"code_sha256":"bdcac6c19196f655","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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/3/float, ratio:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"bdcac6c19196f655"},"code_page":"/code/interpolate","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bdcac6c19196f655"}},{"code_sha256":"360a191dd28ceec7","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,"code_page":"/code/get-decoder","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"360a191dd28ceec7"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"83eb4a13f9650ee9c86a6cea8f5a114f0f37db5958db2a0e2e6ea1fead20a8b0","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}