{"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/whispering-llama-a-cross-modal-generative","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","arxiv_id":"2310.06434","date":"2023-10-10","proceeding":null,"authors":["Srijith Radhakrishnan","Chao-Han Huck Yang","Sumeer Ahmad Khan","Rohit Kumar","Narsis A. Kiani","David Gomez-Cabrero","Jesper N. Tegner"],"abstract":"We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate speech transcription contexts. This marks a step towards a fresh paradigm in generative error correction within the realm of n-best hypotheses. Unlike the existing ranking-based rescoring methods, our approach adeptly uses distinct initialization techniques and parameter-efficient algorithms to boost ASR performance derived from pre-trained speech and text models. Through evaluation across diverse ASR datasets, we evaluate the stability and reproducibility of our fusion technique, demonstrating its improved word error rate relative (WERR) performance in comparison to n-best hypotheses by relatively 37.66%. To encourage future research, we have made our code and pre-trained models open source at https://github.com/Srijith-rkr/Whispering-LLaMA.","url_abs":"https://arxiv.org/abs/2310.06434v2","url_pdf":"https://arxiv.org/pdf/2310.06434v2.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":"whispering-llama-a-cross-modal-generative","repo_url":"https://github.com/srijith-rkr/whispering-llama","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/automatic-speech-recognition-on-lrs2","task":"Automatic Speech Recognition (ASR)","dataset":"LRS2","model":"Whisper-LLaMA","rank_in_archive_order":5,"of":9,"metrics":{"Test WER":"6.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.06434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06434"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/srijith-rkr/whispering-llama","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_honours":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"9f25faffc096d186","entry":"adapter_state_from_state_dict","repo":"srijith-rkr/whispering-llama","repo_kind":"official","path":"lit_llama/WL.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/WL.py","link_basis":"first_harvest_node","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":"9f25faffc096d186"}},{"code_sha256_prefix":"8a187cb05b43141d","entry":"build_rope_cache","repo":"srijith-rkr/whispering-llama","repo_kind":"official","path":"lit_llama/model.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/model.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a187cb05b43141d"}},{"code_sha256_prefix":"aba86ffbed27ba65","entry":"find_multiple","repo":"srijith-rkr/whispering-llama","repo_kind":"official","path":"lit_llama/utils.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aba86ffbed27ba65"}},{"code_sha256_prefix":"14e0b2570cf485fe","entry":"llama_model_lookup","repo":"srijith-rkr/whispering-llama","repo_kind":"official","path":"lit_llama/utils.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/utils.py","link_basis":"first_harvest_node","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":"14e0b2570cf485fe"}},{"code_sha256_prefix":"7137105772c52074","entry":"apply_rope","repo":"srijith-rkr/whispering-llama","repo_kind":"official","path":"lit_llama/model.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/model.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":"7137105772c52074"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}