{"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/hifi-gan-generative-adversarial-networks-for","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","arxiv_id":"2010.05646","date":"2020-10-12","proceeding":"NeurIPS 2020) 2020 10","authors":["Jungil Kong","Jaehyeon Kim","Jaekyoung Bae"],"abstract":"Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of autoregressive and flow-based generative models. In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. As speech audio consists of sinusoidal signals with various periods, we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. A subjective human evaluation (mean opinion score, MOS) of a single speaker dataset indicates that our proposed method demonstrates similarity to human quality while generating 22.05 kHz high-fidelity audio 167.9 times faster than real-time on a single V100 GPU. We further show the generality of HiFi-GAN to the mel-spectrogram inversion of unseen speakers and end-to-end speech synthesis. Finally, a small footprint version of HiFi-GAN generates samples 13.4 times faster than real-time on CPU with comparable quality to an autoregressive counterpart.","url_abs":"https://arxiv.org/abs/2010.05646v2","url_pdf":"https://arxiv.org/pdf/2010.05646v2.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":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/jik876/hifi-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/TensorSpeech/TensorflowTTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/jaywalnut310/glow-tts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/keonlee9420/Comprehensive-E2E-TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/maum-ai/univnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/mindslab-ai/univnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/rishikksh20/HiFi-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/takaaki-saeki/ssl_speech_restoration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/IAHispano/Applio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","repo_url":"https://github.com/NVIDIA/DeepLearningExamples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"hifi-gan-generative-adversarial-networks-for","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"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[{"method_slug":"hifi-gan","method_name":"HiFi-GAN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"hifi-gan","name":"HiFi-GAN","full_name":"HiFi-GAN"}],"results":[{"leaderboard":"/sota/speech-synthesis-on-libritts","task":"Speech Synthesis","dataset":"LibriTTS","model":"HiFi-GAN","rank_in_archive_order":14,"of":15,"metrics":{"M-STFT":"1.0017","MCD":"0.6603","PESQ":"2.947","Periodicity":" 0.1565","V/UV F1":"0.9300"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.05646","atlas_url":"https://app.syntology.ai/?focus=2010.05646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05646"}},"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/DeepLearningExamples","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaywalnut310/glow-tts","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jik876/hifi-gan","reach":null},{"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/rishikksh20/HiFi-GAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TensorSpeech/TensorflowTTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/takaaki-saeki/ssl_speech_restoration","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindslab-ai/univnet","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IAHispano/Applio","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maum-ai/univnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/Comprehensive-E2E-TTS","reach":null}],"summary":{"ran_draft_wrong":3,"ran":14,"unverified":8},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1},"listed":{"samples":20,"ran":12,"repositories":6}},"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":3,"samples":[{"code_sha256_prefix":"1644a2f2942ffe4c","entry":"load_checkpoint","repo":"jik876/hifi-gan","repo_kind":"official","path":"inference.py","file_url":"https://github.com/jik876/hifi-gan/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1644a2f2942ffe4c"}},{"code_sha256_prefix":"1cbd5983017dbccf","entry":"DiscriminatorP","repo":"keonlee9420/Comprehensive-E2E-TTS","repo_kind":"listed","path":"model/E2ETTS.py","file_url":"https://github.com/keonlee9420/Comprehensive-E2E-TTS/blob/HEAD/model/E2ETTS.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":"1cbd5983017dbccf"}},{"code_sha256_prefix":"a8588b06fe6ee564","entry":"Generator","repo":"takaaki-saeki/ssl_speech_restoration","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/takaaki-saeki/ssl_speech_restoration/blob/HEAD/hifigan/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8588b06fe6ee564"}},{"code_sha256_prefix":"315da86169871441","entry":"Generator","repo":"rishikksh20/HiFi-GAN","repo_kind":"listed","path":"model/generator.py","file_url":"https://github.com/rishikksh20/HiFi-GAN/blob/HEAD/model/generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"315da86169871441"}},{"code_sha256_prefix":"a02c998d88e55794","entry":"Generator","repo":"jik876/hifi-gan","repo_kind":"official","path":"models.py","file_url":"https://github.com/jik876/hifi-gan/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a02c998d88e55794"}},{"code_sha256_prefix":"296fba6a2e3878dd","entry":"MRF","repo":"rishikksh20/HiFi-GAN","repo_kind":"listed","path":"model/generator.py","file_url":"https://github.com/rishikksh20/HiFi-GAN/blob/HEAD/model/generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"296fba6a2e3878dd"}},{"code_sha256_prefix":"e51b96d3f2bca97c","entry":"MultiPeriodDiscriminator","repo":"keonlee9420/Comprehensive-E2E-TTS","repo_kind":"listed","path":"model/E2ETTS.py","file_url":"https://github.com/keonlee9420/Comprehensive-E2E-TTS/blob/HEAD/model/E2ETTS.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":"e51b96d3f2bca97c"}},{"code_sha256_prefix":"6dd04160990ce7aa","entry":"ResBlock1","repo":"takaaki-saeki/ssl_speech_restoration","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/takaaki-saeki/ssl_speech_restoration/blob/HEAD/hifigan/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dd04160990ce7aa"}},{"code_sha256_prefix":"e9c63f1724d52ed8","entry":"ResBlock1","repo":"jik876/hifi-gan","repo_kind":"official","path":"models.py","file_url":"https://github.com/jik876/hifi-gan/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9c63f1724d52ed8"}},{"code_sha256_prefix":"29a9e53b37e5a897","entry":"ResBlock2","repo":"takaaki-saeki/ssl_speech_restoration","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/takaaki-saeki/ssl_speech_restoration/blob/HEAD/hifigan/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29a9e53b37e5a897"}},{"code_sha256_prefix":"d7373d3c5d20dd29","entry":"ResBlock2","repo":"jik876/hifi-gan","repo_kind":"official","path":"models.py","file_url":"https://github.com/jik876/hifi-gan/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7373d3c5d20dd29"}},{"code_sha256_prefix":"cec55aeff5fee127","entry":"ResStack","repo":"rishikksh20/HiFi-GAN","repo_kind":"listed","path":"model/generator.py","file_url":"https://github.com/rishikksh20/HiFi-GAN/blob/HEAD/model/generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cec55aeff5fee127"}},{"code_sha256_prefix":"47841da7a9730802","entry":"TFMultiHifiResBlock","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"47841da7a9730802"}},{"code_sha256_prefix":"4ab0d0201baa1a43","entry":"TFReflectionPad1d","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ab0d0201baa1a43"}},{"code_sha256_prefix":"b73dd2a7fa701451","entry":"WeightNormalization","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b73dd2a7fa701451"}},{"code_sha256_prefix":"e3ecb51f94828d3b","entry":"get_initializer","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3ecb51f94828d3b"}},{"code_sha256_prefix":"404632cb4f4669da","entry":"scan_checkpoint","repo":"jik876/hifi-gan","repo_kind":"official","path":"inference.py","file_url":"https://github.com/jik876/hifi-gan/blob/HEAD/inference.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"404632cb4f4669da"}},{"code_sha256_prefix":"3193c0ceab116156","entry":"BaseModel","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","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":"3193c0ceab116156"}},{"code_sha256_prefix":"793b82863c1fdc65","entry":"Generator","repo":"maum-ai/univnet","repo_kind":"listed","path":"model/generator.py","file_url":"https://github.com/maum-ai/univnet/blob/HEAD/model/generator.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":"793b82863c1fdc65"}},{"code_sha256_prefix":"788fd01770c36aed","entry":"KernelPredictor","repo":"maum-ai/univnet","repo_kind":"listed","path":"model/generator.py","file_url":"https://github.com/maum-ai/univnet/blob/HEAD/model/generator.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":"788fd01770c36aed"}},{"code_sha256_prefix":"ddf586275727eb6a","entry":"LVCBlock","repo":"maum-ai/univnet","repo_kind":"listed","path":"model/generator.py","file_url":"https://github.com/maum-ai/univnet/blob/HEAD/model/generator.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":"ddf586275727eb6a"}},{"code_sha256_prefix":"770d53e113359a0f","entry":"TFConvTranspose1d","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","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":"770d53e113359a0f"}},{"code_sha256_prefix":"ed16adff529066e2","entry":"TFHifiGANGenerator","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","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":"ed16adff529066e2"}},{"code_sha256_prefix":"90a00ab9b14ddecf","entry":"TFHifiResBlock","repo":"TensorSpeech/TensorflowTTS","repo_kind":"listed","path":"tensorflow_tts/models/hifigan.py","file_url":"https://github.com/TensorSpeech/TensorflowTTS/blob/HEAD/tensorflow_tts/models/hifigan.py","link_basis":"first_harvest_node","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":"90a00ab9b14ddecf"}},{"code_sha256_prefix":"b170cd48d4da4c05","entry":"_convert_ts_to_trt_hifigan","repo":"NVIDIA/DeepLearningExamples","repo_kind":"listed","path":"PyTorch/SpeechSynthesis/HiFiGAN/models.py","file_url":"https://github.com/NVIDIA/DeepLearningExamples/blob/HEAD/PyTorch/SpeechSynthesis/HiFiGAN/models.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":"b170cd48d4da4c05"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}