LatentSync/configs/audio.yaml

audio:
  num_mels: 80 # Number of mel-spectrogram channels and local conditioning dimensionality
  rescale: true # Whether to rescale audio prior to preprocessing
  rescaling_max: 0.9 # Rescaling value
  use_lws:
    false # Use LWS (https://github.com/Jonathan-LeRoux/lws) for STFT and phase reconstruction
    # It"s preferred to set True to use with https://github.com/r9y9/wavenet_vocoder
    # Does not work if n_ffit is not multiple of hop_size!!
  n_fft: 800 # Extra window size is filled with 0 paddings to match this parameter
  hop_size: 200 # For 16000Hz, 200 = 12.5 ms (0.0125 * sample_rate)
  win_size: 800 # For 16000Hz, 800 = 50 ms (If None, win_size = n_fft) (0.05 * sample_rate)
  sample_rate: 16000 # 16000Hz (corresponding to librispeech) (sox --i <filename>)
  frame_shift_ms: null
  signal_normalization: true
  allow_clipping_in_normalization: true
  symmetric_mels: true
  max_abs_value: 4.0
  preemphasize: true # whether to apply filter
  preemphasis: 0.97 # filter coefficient.
  min_level_db: -100
  ref_level_db: 20
  fmin: 55
  fmax: 7600