TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/Vocos

Vocos

Reported on 9 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.

Audio9 results

  • Speech RecognitiononLibriTTS
    PESQ· 2023-06-01
    3.7
    best: 4.454 (PeriodWave-Turbo-L)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Speech RecognitiononLibriTTS
    Periodicity· 2023-06-01
    0.101
    best: 0.3044 (SC-WaveRNN)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Speech RecognitiononLibriTTS
    V/UV F1· 2023-06-01
    0.9582
    best: 0.9793 (BigVGAN-v2)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Speech SynthesisonLibriTTS
    PESQ· 2023-06-01
    3.7
    best: 4.454 (PeriodWave-Turbo-L)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Speech SynthesisonLibriTTS
    Periodicity· 2023-06-01
    0.101
    best: 0.3044 (SC-WaveRNN)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Speech SynthesisonLibriTTS
    V/UV F1· 2023-06-01
    0.9582
    best: 0.9793 (BigVGAN-v2)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Accented Speech RecognitiononLibriTTS
    PESQ· 2023-06-01
    3.7
    best: 4.454 (PeriodWave-Turbo-L)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Accented Speech RecognitiononLibriTTS
    Periodicity· 2023-06-01
    0.101
    best: 0.3044 (SC-WaveRNN)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814
  • Accented Speech RecognitiononLibriTTS
    V/UV F1· 2023-06-01
    0.9582
    best: 0.9793 (BigVGAN-v2)
    Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisarXiv:2306.00814