{"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/whisper-flamingo-integrating-visual-features","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","arxiv_id":"2406.10082","date":"2024-06-14","proceeding":null,"authors":["Andrew Rouditchenko","Yuan Gong","Samuel Thomas","Leonid Karlinsky","Hilde Kuehne","Rogerio Feris","James Glass"],"abstract":"Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast, speech models such as Whisper are trained with hundreds of thousands of hours of data, and thus learn a better speech-to-text decoder. The huge training data difference motivates us to adapt Whisper to handle video inputs. Inspired by Flamingo which injects visual features into language models, we propose Whisper-Flamingo which integrates visual features into the Whisper speech recognition and translation model with gated cross attention. Our models achieve state-of-the-art ASR WER (0.68%) and AVSR WER (0.76%) on LRS3, and state-of-the-art ASR WER (1.3%) and AVSR WER (1.4%) on LRS2. Audio-visual Whisper-Flamingo outperforms audio-only Whisper on English speech recognition and En-X translation for 6 languages in noisy conditions. Moreover, Whisper-Flamingo is versatile and conducts all of these tasks using one set of parameters, while prior methods are trained separately on each language.","url_abs":"https://arxiv.org/abs/2406.10082v3","url_pdf":"https://arxiv.org/pdf/2406.10082v3.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":"whisper-flamingo-integrating-visual-features","repo_url":"https://github.com/roudimit/whisper-flamingo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"audio-visual-speech-recognition","task_name":"Audio-Visual Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs2","task":"Audio-Visual Speech Recognition","dataset":"LRS2","model":"Whisper-Flamingo","rank_in_archive_order":1,"of":8,"metrics":{"Test WER":"1.4"},"uses_additional_data":true},{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs3-ted","task":"Audio-Visual Speech Recognition","dataset":"LRS3-TED","model":"Whisper-Flamingo","rank_in_archive_order":2,"of":12,"metrics":{"Word Error Rate (WER)":"0.76"},"uses_additional_data":true},{"leaderboard":"/sota/automatic-speech-recognition-on-lrs2","task":"Automatic Speech Recognition (ASR)","dataset":"LRS2","model":"Whisper","rank_in_archive_order":1,"of":9,"metrics":{"Test WER":"1.3"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-lrs3-ted","task":"Speech Recognition","dataset":"LRS3-TED","model":"Whisper","rank_in_archive_order":1,"of":4,"metrics":{"Word Error Rate (WER)":"0.68"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10082"}},"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/roudimit/whisper-flamingo","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1,"ran":2,"ran_honours":2,"unverified":13},"by_repo_kind":{"official":{"samples":18,"ran":5,"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":18,"samples":[{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/resnet.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"d50e3a8f0b0f9a21","entry":"downsample_basic_block","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/resnet.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d50e3a8f0b0f9a21"}},{"code_sha256_prefix":"546a770034e200d1","entry":"downsample_basic_block_v2","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/resnet.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"546a770034e200d1"}},{"code_sha256_prefix":"6e0808fc4828513a","entry":"exact_div","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/utils.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/utils.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e0808fc4828513a"}},{"code_sha256_prefix":"e529c9641c178fe0","entry":"sinusoids","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/model.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"code_sha256_prefix":"41c654294ba9ec56","entry":"backtrace","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/timing.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/timing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"41c654294ba9ec56"}},{"code_sha256_prefix":"76330ed965e60af5","entry":"dtw_cpu","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/timing.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/timing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"76330ed965e60af5"}},{"code_sha256_prefix":"1549b2f905088001","entry":"get_encoding","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/tokenizer.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1549b2f905088001"}},{"code_sha256_prefix":"7929dec299b10283","entry":"get_tokenizer","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/tokenizer.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7929dec299b10283"}},{"code_sha256_prefix":"80abc0b281d75575","entry":"load_audio","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/audio.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80abc0b281d75575"}},{"code_sha256_prefix":"6e70207ad77f0ae6","entry":"median_filter","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/timing.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/timing.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e70207ad77f0ae6"}},{"code_sha256_prefix":"27325bde549014b8","entry":"median_filter_cuda","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/triton_ops.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/triton_ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"27325bde549014b8"}},{"code_sha256_prefix":"b946e8e3af390ae7","entry":"median_kernel","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/triton_ops.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/triton_ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b946e8e3af390ae7"}},{"code_sha256_prefix":"12c6c409a1e359c3","entry":"mel_filters","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/audio.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"12c6c409a1e359c3"}},{"code_sha256_prefix":"e56996b20b9c19cb","entry":"optional_int","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/utils.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e56996b20b9c19cb"}},{"code_sha256_prefix":"9f13de1c23e4003d","entry":"pad_or_trim","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/audio.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"code_sha256_prefix":"176b6ba6c2c2940c","entry":"str2bool","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/utils.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"176b6ba6c2c2940c"}},{"code_sha256_prefix":"7bebc0cb7f2ab5b0","entry":"transcribe","repo":"roudimit/whisper-flamingo","repo_kind":"official","path":"whisper/transcribe.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/transcribe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7bebc0cb7f2ab5b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}