{"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/sequence-to-sequence-piano-transcription-with","title":"Sequence-to-Sequence Piano Transcription with Transformers","arxiv_id":"2107.09142","date":"2021-07-19","proceeding":null,"authors":["Curtis Hawthorne","Ian Simon","Rigel Swavely","Ethan Manilow","Jesse Engel"],"abstract":"Automatic Music Transcription has seen significant progress in recent years by training custom deep neural networks on large datasets. However, these models have required extensive domain-specific design of network architectures, input/output representations, and complex decoding schemes. In this work, we show that equivalent performance can be achieved using a generic encoder-decoder Transformer with standard decoding methods. We demonstrate that the model can learn to translate spectrogram inputs directly to MIDI-like output events for several transcription tasks. This sequence-to-sequence approach simplifies transcription by jointly modeling audio features and language-like output dependencies, thus removing the need for task-specific architectures. These results point toward possibilities for creating new Music Information Retrieval models by focusing on dataset creation and labeling rather than custom model design.","url_abs":"https://arxiv.org/abs/2107.09142v1","url_pdf":"https://arxiv.org/pdf/2107.09142v1.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":"sequence-to-sequence-piano-transcription-with","repo_url":"https://github.com/rlax59us/MT3-MAESTRO-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sequence-to-sequence-piano-transcription-with","repo_url":"https://github.com/Aolin-MIR/Sequence-to-Sequence-Piano-Transcription-with-Transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"music-information-retrieval","task_name":"Music Information Retrieval"},{"task_slug":"music-transcription","task_name":"Music Transcription"},{"task_slug":"retrieval","task_name":"Retrieval"}],"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":"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.09142","atlas_url":"https://app.syntology.ai/?focus=2107.09142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09142"}},"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/rlax59us/MT3-MAESTRO-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Aolin-MIR/Sequence-to-Sequence-Piano-Transcription-with-Transformers","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":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":2,"samples":[{"code_sha256_prefix":"b8dbb49c5ff1b7c6","entry":"note_4f1_loss","repo":"Aolin-MIR/Sequence-to-Sequence-Piano-Transcription-with-Transformers","repo_kind":"listed","path":"torch_train.py","file_url":"https://github.com/Aolin-MIR/Sequence-to-Sequence-Piano-Transcription-with-Transformers/blob/HEAD/torch_train.py","link_basis":"first_harvest_node","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":"b8dbb49c5ff1b7c6"}},{"code_sha256_prefix":"cde8bbd8b571ca5c","entry":"parse_fn","repo":"Aolin-MIR/Sequence-to-Sequence-Piano-Transcription-with-Transformers","repo_kind":"listed","path":"torch_train.py","file_url":"https://github.com/Aolin-MIR/Sequence-to-Sequence-Piano-Transcription-with-Transformers/blob/HEAD/torch_train.py","link_basis":"first_harvest_node","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":"cde8bbd8b571ca5c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}