{"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/conformer-convolution-augmented-transformer","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","arxiv_id":"2005.08100","date":"2020-05-16","proceeding":null,"authors":["Anmol Gulati","James Qin","Chung-Cheng Chiu","Niki Parmar","Yu Zhang","Jiahui Yu","Wei Han","Shibo Wang","Zhengdong Zhang","Yonghui Wu","Ruoming Pang"],"abstract":"Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother. We also observe competitive performance of 2.7%/6.3% with a small model of only 10M parameters.","url_abs":"https://arxiv.org/abs/2005.08100v1","url_pdf":"https://arxiv.org/pdf/2005.08100v1.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":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/HarunoriKawano/Conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/Joshuaoneheart/Fintech-Final-Report","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/MagicHub-io/Magic-Data-ASR-SD-Challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/Rishit-dagli/Conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/TeaPoly/Conformer-Athena","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/TensorSpeech/TensorFlowASR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/alibaba-damo-academy/FunASR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/augustgw/early-exit-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/jaketae/conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/keonlee9420/Comprehensive-Transformer-TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/lucidrains/conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/lucidrains/soundstorm-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/msalhab96/Conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/msalhab96/SpeeQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/openspeech-team/openspeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/park-cheol/ASR-Conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/phanxuanphucnd/Arizona-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/phanxuanphucnd/conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/seongho608/ringformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/sooftware/OpenSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/sooftware/conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/tuanio/nextformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/PaddlePaddle/PaddleSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/tuanio/conformer-rnnt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"conformer-convolution-augmented-transformer","repo_url":"https://github.com/wenet-e2e/wenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Conformer(L)","rank_in_archive_order":18,"of":64,"metrics":{"Word Error Rate (WER)":"1.9"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Conformer(M)","rank_in_archive_order":22,"of":64,"metrics":{"Word Error Rate (WER)":"2"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Conformer(S)","rank_in_archive_order":30,"of":64,"metrics":{"Word Error Rate (WER)":"2.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Conformer(L)","rank_in_archive_order":14,"of":53,"metrics":{"Word Error Rate (WER)":"3.9"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Conformer(M)","rank_in_archive_order":23,"of":53,"metrics":{"Word Error Rate (WER)":"4.3"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Conformer(S)","rank_in_archive_order":31,"of":53,"metrics":{"Word Error Rate (WER)":"5.0"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08100"}},"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/wenet-e2e/wenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TensorSpeech/TensorFlowASR","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSpeech","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TeaPoly/Conformer-Athena","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phanxuanphucnd/conformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba-damo-academy/FunASR","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/soundstorm-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HarunoriKawano/Conformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MagicHub-io/Magic-Data-ASR-SD-Challenge","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phanxuanphucnd/Arizona-asr","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaketae/conformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sooftware/OpenSpeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seongho608/ringformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sooftware/conformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tuanio/nextformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/park-cheol/ASR-Conformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Rishit-dagli/Conformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/Comprehensive-Transformer-TTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Joshuaoneheart/Fintech-Final-Report","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msalhab96/SpeeQ","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msalhab96/Conformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/augustgw/early-exit-transformer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openspeech-team/openspeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/conformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tuanio/conformer-rnnt","reach":{"status":"ok"}}],"summary":{"ran_violates":3,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":5,"ran":2,"repositories":5}},"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":2,"samples":[{"code_sha256_prefix":"a41cb31b42e919b1","entry":"calc_same_padding","repo":"lucidrains/conformer","repo_kind":"listed","path":"conformer/conformer.py","file_url":"https://github.com/lucidrains/conformer/blob/HEAD/conformer/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a41cb31b42e919b1"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"2835e46864d2299b","entry":"get_speakers","repo":"TeaPoly/Conformer-Athena","repo_kind":"listed","path":"examples/asr/timit/local/prepare_data.py","file_url":"https://github.com/TeaPoly/Conformer-Athena/blob/HEAD/examples/asr/timit/local/prepare_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2835e46864d2299b"}},{"code_sha256_prefix":"d759ddcfb8763ee8","entry":"check_token","repo":"msalhab96/Conformer","repo_kind":"listed","path":"tokenizer.py","file_url":"https://github.com/msalhab96/Conformer/blob/HEAD/tokenizer.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":"d759ddcfb8763ee8"}},{"code_sha256_prefix":"efd738a0bc3cc757","entry":"deserialize","repo":"TensorSpeech/TensorFlowASR","repo_kind":"listed","path":"tensorflow_asr/callbacks.py","file_url":"https://github.com/TensorSpeech/TensorFlowASR/blob/HEAD/tensorflow_asr/callbacks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"efd738a0bc3cc757"}},{"code_sha256_prefix":"746f1b671084d3ba","entry":"skew","repo":"jaketae/conformer","repo_kind":"listed","path":"conformer/attention.py","file_url":"https://github.com/jaketae/conformer/blob/HEAD/conformer/attention.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":"746f1b671084d3ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}