Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/HiFi-GAN

HiFi-GAN

Reported on 15 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio15 results

Speech RecognitiononLibriTTS
M-STFT· 2020-10-12
1.0017
best: 2.2358 (SC-WaveRNN)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech RecognitiononLibriTTS
MCD· 2020-10-12
0.6603
best: 2.3591 (WaveGlow)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech RecognitiononLibriTTS
PESQ· 2020-10-12
2.947
best: 4.454 (PeriodWave-Turbo-L)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech RecognitiononLibriTTS
Periodicity· 2020-10-12
0.1565
best: 0.3044 (SC-WaveRNN)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech RecognitiononLibriTTS
V/UV F1· 2020-10-12
0.93
best: 0.9793 (BigVGAN-v2)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech SynthesisonLibriTTS
M-STFT· 2020-10-12
1.0017
best: 2.2358 (SC-WaveRNN)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech SynthesisonLibriTTS
MCD· 2020-10-12
0.6603
best: 2.3591 (WaveGlow)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech SynthesisonLibriTTS
PESQ· 2020-10-12
2.947
best: 4.454 (PeriodWave-Turbo-L)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech SynthesisonLibriTTS
Periodicity· 2020-10-12
0.1565
best: 0.3044 (SC-WaveRNN)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Speech SynthesisonLibriTTS
V/UV F1· 2020-10-12
0.93
best: 0.9793 (BigVGAN-v2)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Accented Speech RecognitiononLibriTTS
M-STFT· 2020-10-12
1.0017
best: 2.2358 (SC-WaveRNN)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Accented Speech RecognitiononLibriTTS
MCD· 2020-10-12
0.6603
best: 2.3591 (WaveGlow)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Accented Speech RecognitiononLibriTTS
PESQ· 2020-10-12
2.947
best: 4.454 (PeriodWave-Turbo-L)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Accented Speech RecognitiononLibriTTS
Periodicity· 2020-10-12
0.1565
best: 0.3044 (SC-WaveRNN)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646
Accented Speech RecognitiononLibriTTS
V/UV F1· 2020-10-12
0.93
best: 0.9793 (BigVGAN-v2)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis arXiv:2010.05646