{"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/waveflow-a-compact-flow-based-model-for-raw-1","title":"WaveFlow: A Compact Flow-based Model for Raw Audio","arxiv_id":"1912.01219","date":"2019-12-03","proceeding":"ICML 2020 1","authors":["Wei Ping","Kainan Peng","Kexin Zhao","Zhao Song"],"abstract":"In this work, we propose WaveFlow, a small-footprint generative flow for raw audio, which is directly trained with maximum likelihood. It handles the long-range structure of 1-D waveform with a dilated 2-D convolutional architecture, while modeling the local variations using expressive autoregressive functions. WaveFlow provides a unified view of likelihood-based models for 1-D data, including WaveNet and WaveGlow as special cases. It generates high-fidelity speech as WaveNet, while synthesizing several orders of magnitude faster as it only requires a few sequential steps to generate very long waveforms with hundreds of thousands of time-steps. Furthermore, it can significantly reduce the likelihood gap that has existed between autoregressive models and flow-based models for efficient synthesis. Finally, our small-footprint WaveFlow has only 5.91M parameters, which is 15$\\times$ smaller than WaveGlow. It can generate 22.05 kHz high-fidelity audio 42.6$\\times$ faster than real-time (at a rate of 939.3 kHz) on a V100 GPU without engineered inference kernels.","url_abs":"https://arxiv.org/abs/1912.01219v4","url_pdf":"https://arxiv.org/pdf/1912.01219v4.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":"waveflow-a-compact-flow-based-model-for-raw-1","repo_url":"https://github.com/PaddlePaddle/Parakeet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"waveflow-a-compact-flow-based-model-for-raw-1","repo_url":"https://github.com/L0SG/NanoFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"waveflow-a-compact-flow-based-model-for-raw-1","repo_url":"https://github.com/L0SG/WaveFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"waveflow-a-compact-flow-based-model-for-raw-1","repo_url":"https://github.com/caillonantoine/waveflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[{"method_slug":"affine-coupling","method_name":"Affine Coupling"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"invertible-1x1-convolution","method_name":"Invertible 1x1 Convolution"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"},{"method_slug":"waveglow","method_name":"WaveGlow"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-synthesis-on-libritts","task":"Speech Synthesis","dataset":"LibriTTS","model":"WaveFlow","rank_in_archive_order":13,"of":15,"metrics":{"M-STFT":"1.1120","MCD":"1.2455","PESQ":"3.027","Periodicity":"0.1416","V/UV F1":"0.9410"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.01219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01219"}},"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/L0SG/NanoFlow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/caillonantoine/waveflow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/Parakeet","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/L0SG/WaveFlow","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":6},"by_repo_kind":{"listed":{"samples":9,"ran":3,"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":"83e2c862f7374ac7","entry":"dynamic_range_compression","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"tacotron2_custom/audio_processing.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/tacotron2_custom/audio_processing.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"83e2c862f7374ac7"}},{"code_sha256_prefix":"87324754644a55a3","entry":"gaussian_sample","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"functions.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/functions.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"87324754644a55a3"}},{"code_sha256_prefix":"9f9ec26d4cdfdf7d","entry":"griffin_lim","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"tacotron2_custom/audio_processing.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/tacotron2_custom/audio_processing.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"code_sha256_prefix":"21e38cc8239d26e5","entry":"bipartize","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"functions.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/functions.py","link_basis":"harvester_set","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":"21e38cc8239d26e5"}},{"code_sha256_prefix":"6e8184ff4faf3139","entry":"files_to_list","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"mel2samp.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/mel2samp.py","link_basis":"harvester_set","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":"6e8184ff4faf3139"}},{"code_sha256_prefix":"4537862a4c53b4c3","entry":"fused_add_tanh_sigmoid_multiply","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"modules.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/modules.py","link_basis":"harvester_set","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":"4537862a4c53b4c3"}},{"code_sha256_prefix":"504a64a95e4d96d6","entry":"fused_res_skip","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"modules.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/modules.py","link_basis":"harvester_set","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":"504a64a95e4d96d6"}},{"code_sha256_prefix":"054f22912d47c960","entry":"gaussian_log_p","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"functions.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/functions.py","link_basis":"harvester_set","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":"054f22912d47c960"}},{"code_sha256_prefix":"50d1245d6b4055c4","entry":"load_wav_to_torch","repo":"L0SG/WaveFlow","repo_kind":"listed","path":"mel2samp.py","file_url":"https://github.com/L0SG/WaveFlow/blob/HEAD/mel2samp.py","link_basis":"harvester_set","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":"50d1245d6b4055c4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}