Papers › HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

12 Oct 2020NeurIPS 2020) 2020 10arXiv:2010.05646archive 2025-07-28

Jungil Kong, Jaehyeon Kim, Jaekyoung Bae

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.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 25 code samples harvested from 7 repositories linked to this paper: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 5 ran (3 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 20 samples from 6 repositories, 12 ran (11 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

jik876/hifi-gan officialmentioned in papermentioned on GitHubpytorchSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
TensorSpeech/TensorflowTTS mentioned on GitHubtfSyntology: 8 samples, 4 ran (1 instrument-failed) · 4 unverified report
jaywalnut310/glow-tts mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech (arXiv:2106.06103; that paper's own run record: 47 ran (of which 12 constructed an object rather than computing a result; 34 with no instrument failure: 2 honoured, 0 violated, 32 with no contract checked; 13 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
keonlee9420/Comprehensive-E2E-TTS mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
maum-ai/univnet mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
mindslab-ai/univnet mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
rishikksh20/HiFi-GAN mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
takaaki-saeki/ssl_speech_restoration mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
IAHispano/Applio pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for... (arXiv:2306.00814; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
NVIDIA/DeepLearningExamples tfSyntology: 1 sample, 0 ran · 1 unverified report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

25 samples harvested: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
14ran
8unverified

Licence: 3 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

jik876/hifi-gan official repository 5 samples, 5 ran (2 instrument-failed) · 0 unverified
load_checkpoint in 277 papers inference.py ran · our draft was wrong MIT (permissive) · 1644a2f2942ffe4c · report fixture: signature filepath:str/0/str, device:device/0/? · returned dict · level recorded, date not recorded
Generator in 95 papers models.py ran MIT (permissive) · a02c998d88e55794 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
ResBlock1 models.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e9c63f1724d52ed8 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
ResBlock2 models.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · d7373d3c5d20dd29 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
scan_checkpoint in 13 papers inference.py ran · our draft was wrong fingerprinted MIT (permissive) · 404632cb4f4669da · report fixture: signature cp_dir:str/0/str, prefix:str/0/str · returned str · level recorded, date not recorded
TensorSpeech/TensorflowTTS community (archive-listed) 8 samples, 4 ran (1 instrument-failed) · 4 unverified
TFMultiHifiResBlock tensorflow_tts/models/hifigan.py ran Apache-2.0 (permissive) · 47841da7a9730802 · report fixture: returned TFMultiHifiResBlock · level recorded 2026-09-22
TFReflectionPad1d tensorflow_tts/models/hifigan.py ran Apache-2.0 (permissive) · 4ab0d0201baa1a43 · report fixture: returned TFReflectionPad1d · level recorded 2026-09-22
WeightNormalization tensorflow_tts/models/hifigan.py ran Apache-2.0 (permissive) · b73dd2a7fa701451 · report fixture: returned WeightNormalization · level recorded 2026-09-22
get_initializer in 32 papers tensorflow_tts/models/hifigan.py ran · our draft was wrong Apache-2.0 (permissive) · e3ecb51f94828d3b · report fixture: signature initializer_seed:int/0/int · returned GlorotNormal · level recorded 2026-09-22
BaseModel in 92 papers tensorflow_tts/models/hifigan.py unverified Apache-2.0 (permissive) · 3193c0ceab116156 · report
TFConvTranspose1d tensorflow_tts/models/hifigan.py unverified Apache-2.0 (permissive) · 770d53e113359a0f · report
TFHifiGANGenerator tensorflow_tts/models/hifigan.py unverified Apache-2.0 (permissive) · ed16adff529066e2 · report
TFHifiResBlock tensorflow_tts/models/hifigan.py unverified Apache-2.0 (permissive) · 90a00ab9b14ddecf · report
keonlee9420/Comprehensive-E2E-TTS community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
DiscriminatorP model/E2ETTS.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1cbd5983017dbccf · report fixture: returned DiscriminatorP · level recorded 2026-09-22
MultiPeriodDiscriminator model/E2ETTS.py ran · metamorphic tier: deterministic no licence file found · pointer only · e51b96d3f2bca97c · report fixture: returned MultiPeriodDiscriminator · level recorded 2026-09-22
maum-ai/univnet community (archive-listed) 3 samples, 0 ran · 3 unverified
Generator in 95 papers model/generator.py unverified BSD-3-Clause (permissive) · 793b82863c1fdc65 · report
KernelPredictor model/generator.py unverified BSD-3-Clause (permissive) · 788fd01770c36aed · report
LVCBlock model/generator.py unverified BSD-3-Clause (permissive) · ddf586275727eb6a · report
rishikksh20/HiFi-GAN community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Generator in 95 papers model/generator.py ran MIT (permissive) · 315da86169871441 · report fixture: returned Generator · level recorded 2026-09-22
MRF model/generator.py ran MIT (permissive) · 296fba6a2e3878dd · report fixture: returned MRF · level recorded 2026-09-22
ResStack model/generator.py ran MIT (permissive) · cec55aeff5fee127 · report fixture: returned ResStack · level recorded 2026-09-22
takaaki-saeki/ssl_speech_restoration community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Generator in 95 papers hifigan/models.py ran MIT (permissive) · a8588b06fe6ee564 · report fixture: returned Generator · level recorded 2026-09-22
ResBlock1 hifigan/models.py ran fingerprinted MIT (permissive) · 6dd04160990ce7aa · report fixture: returned ResBlock1 · level recorded 2026-09-22
ResBlock2 hifigan/models.py ran fingerprinted MIT (permissive) · 29a9e53b37e5a897 · report fixture: returned ResBlock2 · level recorded 2026-09-22
NVIDIA/DeepLearningExamples community (archive-listed) 1 sample, 0 ran · 1 unverified
_convert_ts_to_trt_hifigan PyTorch/SpeechSynthesis/HiFiGAN/models.py unverified no licence file found · pointer only · b170cd48d4da4c05 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

7 sibling assemblies for HiFi-GAN (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. MultiPeriodDiscriminator entry · level 1 · ran · e51b96d3f2bca97c
  2. DiscriminatorP model · level 1 · ran · 1cbd5983017dbccf
  3. get_padding helper · level 1 · ran · honoured contract · a26f85d7c72ef39a

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 8 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. TFHifiGANGenerator entry · level 0 · unverified · ed16adff529066e2
  2. BaseModel helper · level 0 · unverified · 3193c0ceab116156
  3. TFConvTranspose1d helper · level 0 · unverified · 770d53e113359a0f
  4. TFHifiResBlock model · level 0 · unverified · 90a00ab9b14ddecf
  5. TFMultiHifiResBlock model · level 1 · ran · 47841da7a9730802
  6. TFReflectionPad1d helper · level 1 · ran · 4ab0d0201baa1a43
  7. WeightNormalization helper · level 1 · ran · b73dd2a7fa701451
  8. get_initializer helper · level 1 · ran · our draft was wrong · e3ecb51f94828d3b

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. _convert_ts_to_trt_hifigan entry · level 0 · unverified · b170cd48d4da4c05

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 5 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Generator entry · level 1 · ran · a8588b06fe6ee564
  2. ResBlock1 helper · level 1 · ran · 6dd04160990ce7aa
  3. ResBlock2 helper · level 1 · ran · 29a9e53b37e5a897
  4. init_weights helper · level 0 · unverified · b6ab401f5185c8e7
  5. get_padding helper · level 1 · ran · honoured contract · a26f85d7c72ef39a

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Generator entry · level 1 · ran · 315da86169871441
  2. MRF model · level 1 · ran · 296fba6a2e3878dd
  3. ResStack model · level 1 · ran · cec55aeff5fee127

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Generator entry · level 0 · unverified · 793b82863c1fdc65
  2. LVCBlock model · level 0 · unverified · ddf586275727eb6a
  3. KernelPredictor model · level 0 · unverified · 788fd01770c36aed

harvested Assembly for HiFi-GAN (graph method: HiFi-GAN). 5 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Generator entry · level 1 · ran · a02c998d88e55794
  2. ResBlock1 model · level 1 · ran · e9c63f1724d52ed8
  3. ResBlock2 model · level 1 · ran · d7373d3c5d20dd29
  4. init_weights helper · level 0 · unverified · b6ab401f5185c8e7
  5. get_padding helper · level 1 · ran · honoured contract · a26f85d7c72ef39a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2010.05646") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Speech Synthesis

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Synthesis LibriTTS HiFi-GAN M-STFT 1.0017 #14 of 15 Archive leaderboard report
Speech Synthesis LibriTTS HiFi-GAN MCD 0.6603 #14 of 15 Archive leaderboard report
Speech Synthesis LibriTTS HiFi-GAN PESQ 2.947 #14 of 15 Archive leaderboard report
Speech Synthesis LibriTTS HiFi-GAN Periodicity 0.1565 #14 of 15 Archive leaderboard report
Speech Synthesis LibriTTS HiFi-GAN V/UV F1 0.9300 #14 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: HiFi-GAN

HiFi-GAN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections