{"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/waveglow-a-flow-based-generative-network-for","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","arxiv_id":"1811.00002","date":"2018-10-31","proceeding":null,"authors":["Ryan Prenger","Rafael Valle","Bryan Catanzaro"],"abstract":"In this paper we propose WaveGlow: a flow-based network capable of generating\nhigh quality speech from mel-spectrograms. WaveGlow combines insights from Glow\nand WaveNet in order to provide fast, efficient and high-quality audio\nsynthesis, without the need for auto-regression. WaveGlow is implemented using\nonly a single network, trained using only a single cost function: maximizing\nthe likelihood of the training data, which makes the training procedure simple\nand stable. Our PyTorch implementation produces audio samples at a rate of more\nthan 500 kHz on an NVIDIA V100 GPU. Mean Opinion Scores show that it delivers\naudio quality as good as the best publicly available WaveNet implementation.\nAll code will be made publicly available online.","url_abs":"http://arxiv.org/abs/1811.00002v1","url_pdf":"http://arxiv.org/pdf/1811.00002v1.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":"waveglow-a-flow-based-generative-network-for","repo_url":"https://github.com/NVIDIA/waveglow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"waveglow-a-flow-based-generative-network-for","repo_url":"https://github.com/yanggeng1995/WaveGlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"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"},{"method_slug":"weight-normalization","method_name":"Weight Normalization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"waveglow","name":"WaveGlow","full_name":"WaveGlow"}],"results":[{"leaderboard":"/sota/speech-synthesis-on-libritts","task":"Speech Synthesis","dataset":"LibriTTS","model":"WaveGlow","rank_in_archive_order":12,"of":15,"metrics":{"M-STFT":"1.3099","MCD":"2.3591","PESQ":"3.138","Periodicity":"0.1485","V/UV F1":"0.9378"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.00002","atlas_url":"https://app.syntology.ai/?focus=1811.00002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00002"}},"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/NVIDIA/waveglow","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yanggeng1995/WaveGlow","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":1,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"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":"b38f9c28c5117398","entry":"fused_add_tanh_sigmoid_multiply","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"glow.py","file_url":"https://github.com/NVIDIA/waveglow/blob/HEAD/glow.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b38f9c28c5117398"}},{"code_sha256_prefix":"50d1245d6b4055c4","entry":"load_wav_to_torch","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"mel2samp.py","file_url":"https://github.com/NVIDIA/waveglow/blob/HEAD/mel2samp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"50d1245d6b4055c4"}},{"code_sha256_prefix":"b13a72233912c0b1","entry":"remove","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"glow.py","file_url":"https://github.com/NVIDIA/waveglow/blob/HEAD/glow.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b13a72233912c0b1"}},{"code_sha256_prefix":"360725578b4657a7","entry":"apply_gradient_allreduce","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"distributed.py","file_url":"https://github.com/NVIDIA/waveglow/blob/HEAD/distributed.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":"360725578b4657a7"}},{"code_sha256_prefix":"6e8184ff4faf3139","entry":"files_to_list","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"mel2samp.py","file_url":"https://github.com/NVIDIA/waveglow/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":"720ec6edbf432e1e","entry":"reduce_tensor","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"distributed.py","file_url":"https://github.com/NVIDIA/waveglow/blob/HEAD/distributed.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":"720ec6edbf432e1e"}},{"code_sha256_prefix":"a9d6d7e0a940e260","entry":"update_model","repo":"NVIDIA/waveglow","repo_kind":"listed","path":"convert_model.py","file_url":"https://github.com/NVIDIA/waveglow/blob/HEAD/convert_model.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":"a9d6d7e0a940e260"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}