TensorFlowTTS/preprocess/ljspeechu_preprocess.yaml

###########################################################
#                FEATURE EXTRACTION SETTING               #
###########################################################
sampling_rate: 44100     # Sampling rate.
fft_size: 2048           # FFT size.
hop_size: 512            # Hop size. (fixed value, don't change)
win_length: 2048         # Window length.
                         # If set to null, it will be the same as fft_size.
window: "hann"           # Window function.
num_mels: 80             # Number of mel basis.
fmin: 20                 # Minimum freq in mel basis calculation.
fmax: 11025               # Maximum frequency in mel basis calculation.
global_gain_scale: 1.0   # Will be multiplied to all of waveform.
trim_silence: false      # Whether to trim the start and end of silence
trim_threshold_in_db: 60 # Need to tune carefully if the recording is not good.
trim_frame_size: 2048    # Frame size in trimming.
trim_hop_size: 512       # Hop size in trimming.
format: "npy"            # Feature file format. Only "npy" is supported.
trim_mfa: false