fastspeech2

Open repos and models their makers tagged fastspeech2, most starred first. The same for everyone.

Voice and audioRepo

Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

  • 10k
  • Python
  • MIT
  • 8 mo ago
open-mmlabTake it
GitHubRepo

fs2-english-telugu

PyTorch implementation of FastSpeech 2 for English and Telugu speech synthesis with a universal HiFi-GAN neural vocoder. The architecture incorporates feed-forward Transformer blocks and a multi-task Variance Adaptor that explicitly predicts phoneme duration, fundamental frequency (F0 in Hz), and energy contours.

  • 0
  • Python
  • 2 wk ago
saad2134Take it
Search GitHub and Hugging Face for fastspeech2

Get , open it once and sign in. Then come back here and press the button again.