Spaces:
Sleeping
Sleeping
File size: 6,055 Bytes
a22eb82 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
from glob import glob
import os
class HParams:
def __init__(self, **kwargs):
self.data = {}
for key, value in kwargs.items():
self.data[key] = value
def __getattr__(self, key):
if key not in self.data:
raise AttributeError("'HParams' object has no attribute %s" % key)
return self.data[key]
def set_hparam(self, key, value):
self.data[key] = value
# Default hyperparameters
hparams = HParams(
num_mels=80, # Number of mel-spectrogram channels and local conditioning dimensionality
# network
rescale=True, # Whether to rescale audio prior to preprocessing
rescaling_max=0.9, # Rescaling value
# 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!!
use_lws=False,
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=None, # Can replace hop_size parameter. (Recommended: 12.5)
# Mel and Linear spectrograms normalization/scaling and clipping
signal_normalization=True,
# Whether to normalize mel spectrograms to some predefined range (following below parameters)
allow_clipping_in_normalization=True, # Only relevant if mel_normalization = True
symmetric_mels=True,
# Whether to scale the data to be symmetric around 0. (Also multiplies the output range by 2,
# faster and cleaner convergence)
max_abs_value=4.,
# max absolute value of data. If symmetric, data will be [-max, max] else [0, max] (Must not
# be too big to avoid gradient explosion,
# not too small for fast convergence)
# Contribution by @begeekmyfriend
# Spectrogram Pre-Emphasis (Lfilter: Reduce spectrogram noise and helps model certitude
# levels. Also allows for better G&L phase reconstruction)
preemphasize=True, # whether to apply filter
preemphasis=0.97, # filter coefficient.
# Limits
min_level_db=-100,
ref_level_db=20,
fmin=55,
# Set this to 55 if your speaker is male! if female, 95 should help taking off noise. (To
# test depending on dataset. Pitch info: male~[65, 260], female~[100, 525])
fmax=7600, # To be increased/reduced depending on data.
###################### Our training parameters #################################
img_size=96,
fps=25,
batch_size=16,
initial_learning_rate=1e-4,
nepochs=300000, ### ctrl + c, stop whenever eval loss is consistently greater than train loss for ~10 epochs
num_workers=20,
checkpoint_interval=3000,
eval_interval=3000,
writer_interval=300,
save_optimizer_state=True,
syncnet_wt=0.0, # is initially zero, will be set automatically to 0.03 later. Leads to faster convergence.
syncnet_batch_size=64,
syncnet_lr=1e-4,
syncnet_eval_interval=1000,
syncnet_checkpoint_interval=10000,
disc_wt=0.07,
disc_initial_learning_rate=1e-4,
)
# Default hyperparameters
hparamsdebug = HParams(
num_mels=80, # Number of mel-spectrogram channels and local conditioning dimensionality
# network
rescale=True, # Whether to rescale audio prior to preprocessing
rescaling_max=0.9, # Rescaling value
# 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!!
use_lws=False,
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=None, # Can replace hop_size parameter. (Recommended: 12.5)
# Mel and Linear spectrograms normalization/scaling and clipping
signal_normalization=True,
# Whether to normalize mel spectrograms to some predefined range (following below parameters)
allow_clipping_in_normalization=True, # Only relevant if mel_normalization = True
symmetric_mels=True,
# Whether to scale the data to be symmetric around 0. (Also multiplies the output range by 2,
# faster and cleaner convergence)
max_abs_value=4.,
# max absolute value of data. If symmetric, data will be [-max, max] else [0, max] (Must not
# be too big to avoid gradient explosion,
# not too small for fast convergence)
# Contribution by @begeekmyfriend
# Spectrogram Pre-Emphasis (Lfilter: Reduce spectrogram noise and helps model certitude
# levels. Also allows for better G&L phase reconstruction)
preemphasize=True, # whether to apply filter
preemphasis=0.97, # filter coefficient.
# Limits
min_level_db=-100,
ref_level_db=20,
fmin=55,
# Set this to 55 if your speaker is male! if female, 95 should help taking off noise. (To
# test depending on dataset. Pitch info: male~[65, 260], female~[100, 525])
fmax=7600, # To be increased/reduced depending on data.
###################### Our training parameters #################################
img_size=96,
fps=25,
batch_size=2,
initial_learning_rate=1e-3,
nepochs=100000, ### ctrl + c, stop whenever eval loss is consistently greater than train loss for ~10 epochs
num_workers=0,
checkpoint_interval=10000,
eval_interval=10,
writer_interval=5,
save_optimizer_state=True,
syncnet_wt=0.0, # is initially zero, will be set automatically to 0.03 later. Leads to faster convergence.
syncnet_batch_size=64,
syncnet_lr=1e-4,
syncnet_eval_interval=10000,
syncnet_checkpoint_interval=10000,
disc_wt=0.07,
disc_initial_learning_rate=1e-4,
)
def hparams_debug_string():
values = hparams.values()
hp = [" %s: %s" % (name, values[name]) for name in sorted(values) if name != "sentences"]
return "Hyperparameters:\n" + "\n".join(hp)
|