lifeiteng/naturalspeech3_facodec

Issues

• Is there a way to extract embeddings for prosody, content and acoustic details?

  #7 opened 2 months ago by iv41879
  0

• prosody和phone量化后的维度不同

  #3 opened 7 months ago by wcr369
  2

• cound facodec extract emotion information from wav?

  #6 opened 3 months ago by jiahong3837
  0

• Is there a language restriction?

  #1 opened 5 months ago by lanyuer
  2

• How does it work with the TTS model?

  #2 opened 7 months ago by guijuzhejiang
  3

• Train Dataset

  #5 opened 6 months ago by ms-dot-k
  0