{"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/masked-autoencoders-that-listen","title":"Masked Autoencoders that Listen","arxiv_id":"2207.06405","date":"2022-07-13","proceeding":null,"authors":["Po-Yao Huang","Hu Xu","Juncheng Li","Alexei Baevski","Michael Auli","Wojciech Galuba","Florian Metze","Christoph Feichtenhofer"],"abstract":"This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers. The decoder then re-orders and decodes the encoded context padded with mask tokens, in order to reconstruct the input spectrogram. We find it beneficial to incorporate local window attention in the decoder, as audio spectrograms are highly correlated in local time and frequency bands. We then fine-tune the encoder with a lower masking ratio on target datasets. Empirically, Audio-MAE sets new state-of-the-art performance on six audio and speech classification tasks, outperforming other recent models that use external supervised pre-training. The code and models will be at https://github.com/facebookresearch/AudioMAE.","url_abs":"https://arxiv.org/abs/2207.06405v3","url_pdf":"https://arxiv.org/pdf/2207.06405v3.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":"masked-autoencoders-that-listen","repo_url":"https://github.com/facebookresearch/audiomae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"masked-autoencoders-that-listen","repo_url":"https://github.com/eml-eda/tle-supervised","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"masked-autoencoders-that-listen","repo_url":"https://github.com/facebookresearch/multimodal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"masked-autoencoders-that-listen","repo_url":"https://github.com/rishikksh20/AudioMAE-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speaker-identification","task_name":"Speaker Identification"}],"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":"mae","method_name":"MAE"},{"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":[{"leaderboard":"/sota/speaker-identification-on-voxceleb1","task":"Speaker Identification","dataset":"VoxCeleb1","model":"AudioMAE (local)","rank_in_archive_order":4,"of":12,"metrics":{"Accuracy":"94.8","Top-1 (%)":"94.8"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-identification-on-voxceleb1","task":"Speaker Identification","dataset":"VoxCeleb1","model":"AudioMAE (global)","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"94.1","Top-1 (%)":"94.1"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.06405","atlas_url":"https://app.syntology.ai/?focus=2207.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06405"}},"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":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/AudioMAE","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eml-eda/tle-supervised","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rishikksh20/AudioMAE-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/multimodal","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/audiomae","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":14,"ran_violates":1,"ran_fixture":1,"ran_honours":1,"unverified":15},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1},"listed":{"samples":28,"ran":16,"repositories":3}},"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":10,"samples":[{"code_sha256_prefix":"3bd6d4930cb3f2f8","entry":"Attention","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bd6d4930cb3f2f8"}},{"code_sha256_prefix":"b20098ca471958b8","entry":"CyclicShift","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b20098ca471958b8"}},{"code_sha256_prefix":"a78cda64d88bd1f2","entry":"FeedForward","repo":"eml-eda/tle-supervised","repo_kind":"listed","path":"models/models_audio_mae.py","file_url":"https://github.com/eml-eda/tle-supervised/blob/HEAD/models/models_audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a78cda64d88bd1f2"}},{"code_sha256_prefix":"084f9fe01c1b3cf0","entry":"MLP","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"084f9fe01c1b3cf0"}},{"code_sha256_prefix":"354dccecc7d137d8","entry":"MultiHeadSelfAttention","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"354dccecc7d137d8"}},{"code_sha256_prefix":"c691b3b94f34ae10","entry":"PatchEmbed","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c691b3b94f34ae10"}},{"code_sha256_prefix":"aaa7fea64dd2b57c","entry":"PatchEmbed_org","repo":"facebookresearch/audiomae","repo_kind":"official","path":"models_mae.py","file_url":"https://github.com/facebookresearch/audiomae/blob/HEAD/models_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"aaa7fea64dd2b57c"}},{"code_sha256_prefix":"c824fe1a650a3f66","entry":"Residual","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c824fe1a650a3f66"}},{"code_sha256_prefix":"22e4ee062fba7a5e","entry":"SwinBlock","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22e4ee062fba7a5e"}},{"code_sha256_prefix":"0caaefeb6252c9e5","entry":"SwinBlock","repo":"eml-eda/tle-supervised","repo_kind":"listed","path":"models/models_audio_mae.py","file_url":"https://github.com/eml-eda/tle-supervised/blob/HEAD/models/models_audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0caaefeb6252c9e5"}},{"code_sha256_prefix":"54a9926f9e0936b8","entry":"Transformer","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54a9926f9e0936b8"}},{"code_sha256_prefix":"8ae2d3c8074c9653","entry":"Transformer","repo":"eml-eda/tle-supervised","repo_kind":"listed","path":"models/models_audio_mae.py","file_url":"https://github.com/eml-eda/tle-supervised/blob/HEAD/models/models_audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ae2d3c8074c9653"}},{"code_sha256_prefix":"d7227307e8862fc8","entry":"WindowAttention","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7227307e8862fc8"}},{"code_sha256_prefix":"6322ff428c4c429a","entry":"WindowAttention","repo":"eml-eda/tle-supervised","repo_kind":"listed","path":"models/models_audio_mae.py","file_url":"https://github.com/eml-eda/tle-supervised/blob/HEAD/models/models_audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6322ff428c4c429a"}},{"code_sha256_prefix":"5b1dded6034b41e3","entry":"create_mask","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b1dded6034b41e3"}},{"code_sha256_prefix":"11b4cbd5cc85097d","entry":"get_2d_sincos_pos_embed","repo":"eml-eda/tle-supervised","repo_kind":"listed","path":"models/models_audio_mae.py","file_url":"https://github.com/eml-eda/tle-supervised/blob/HEAD/models/models_audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"11b4cbd5cc85097d"}},{"code_sha256_prefix":"ea931f8eaca3c48c","entry":"get_relative_distances","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea931f8eaca3c48c"}},{"code_sha256_prefix":"c263573424bacb51","entry":"AudioMaskedAutoencoderViT","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","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":"c263573424bacb51"}},{"code_sha256_prefix":"b9ab992d4f387299","entry":"AudioMaskedAutoencoderViT","repo":"eml-eda/tle-supervised","repo_kind":"listed","path":"models/models_audio_mae.py","file_url":"https://github.com/eml-eda/tle-supervised/blob/HEAD/models/models_audio_mae.py","link_basis":"first_harvest_node","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":"b9ab992d4f387299"}},{"code_sha256_prefix":"a848037ef9265b59","entry":"MAEOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a848037ef9265b59"}},{"code_sha256_prefix":"680afbcfbca11fb9","entry":"MaskedAutoEncoder","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"680afbcfbca11fb9"}},{"code_sha256_prefix":"28128850f3b7974d","entry":"MaskedAutoencoderViT","repo":"facebookresearch/audiomae","repo_kind":"official","path":"models_mae.py","file_url":"https://github.com/facebookresearch/audiomae/blob/HEAD/models_mae.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":"28128850f3b7974d"}},{"code_sha256_prefix":"d28d7b155c97688a","entry":"PatchEmbed_new","repo":"facebookresearch/audiomae","repo_kind":"official","path":"models_mae.py","file_url":"https://github.com/facebookresearch/audiomae/blob/HEAD/models_mae.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":"d28d7b155c97688a"}},{"code_sha256_prefix":"fef623fdfcfbe69b","entry":"SwinTransformer","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fef623fdfcfbe69b"}},{"code_sha256_prefix":"599cc34da67f0356","entry":"SwinTransformerBlock","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"599cc34da67f0356"}},{"code_sha256_prefix":"fd67d2fafb66524c","entry":"TransformerEncoder","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fd67d2fafb66524c"}},{"code_sha256_prefix":"7a00feceab29852a","entry":"TransformerEncoderLayer","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7a00feceab29852a"}},{"code_sha256_prefix":"f7d645cfcd41319b","entry":"TransformerOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f7d645cfcd41319b"}},{"code_sha256_prefix":"bcffcc5e0273f4c1","entry":"WindowMultiHeadAttention","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"bcffcc5e0273f4c1"}},{"code_sha256_prefix":"8efb3224591920ef","entry":"audio_mae","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8efb3224591920ef"}},{"code_sha256_prefix":"4dafab91858a28d2","entry":"get_2d_sincos_pos_embed","repo":"rishikksh20/AudioMAE-pytorch","repo_kind":"listed","path":"audio_mae.py","file_url":"https://github.com/rishikksh20/AudioMAE-pytorch/blob/HEAD/audio_mae.py","link_basis":"first_harvest_node","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":"4dafab91858a28d2"}},{"code_sha256_prefix":"728825dfce4fad97","entry":"get_2d_sincos_pos_embed_flexible","repo":"facebookresearch/audiomae","repo_kind":"official","path":"models_mae.py","file_url":"https://github.com/facebookresearch/audiomae/blob/HEAD/models_mae.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":"728825dfce4fad97"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}