Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
TensorSpeech
GitHub Repository: TensorSpeech/TensorFlowTTS
Path: blob/master/preprocess/ljspeech_preprocess.yaml
1558 views
1
###########################################################
2
# FEATURE EXTRACTION SETTING #
3
###########################################################
4
sampling_rate: 22050 # Sampling rate.
5
fft_size: 1024 # FFT size.
6
hop_size: 256 # Hop size. (fixed value, don't change)
7
win_length: null # Window length.
8
# If set to null, it will be the same as fft_size.
9
window: "hann" # Window function.
10
num_mels: 80 # Number of mel basis.
11
fmin: 80 # Minimum freq in mel basis calculation.
12
fmax: 7600 # Maximum frequency in mel basis calculation.
13
global_gain_scale: 1.0 # Will be multiplied to all of waveform.
14
trim_silence: true # Whether to trim the start and end of silence.
15
trim_threshold_in_db: 60 # Need to tune carefully if the recording is not good.
16
trim_frame_size: 2048 # Frame size in trimming.
17
trim_hop_size: 512 # Hop size in trimming.
18
format: "npy" # Feature file format. Only "npy" is supported.
19
20
21