liangym
3 years ago
parent
6fb281ca8a
commit
ef7d15dc02
@ -0,0 +1,148 @@
|
|||||||
|
###########################################################
|
||||||
|
# FEATURE EXTRACTION SETTING #
|
||||||
|
###########################################################
|
||||||
|
|
||||||
|
fs: 24000 # sr
|
||||||
|
n_fft: 512 # FFT size (samples).
|
||||||
|
n_shift: 128 # Hop size (samples). 12.5ms
|
||||||
|
win_length: 512 # Window length (samples). 50ms
|
||||||
|
# If set to null, it will be the same as fft_size.
|
||||||
|
window: "hann" # Window function.
|
||||||
|
|
||||||
|
# Only used for feats_type != raw
|
||||||
|
|
||||||
|
fmin: 30 # Minimum frequency of Mel basis.
|
||||||
|
fmax: 12000 # Maximum frequency of Mel basis.
|
||||||
|
n_mels: 80 # The number of mel basis.
|
||||||
|
|
||||||
|
# Only used for the model using pitch features (e.g. FastSpeech2)
|
||||||
|
f0min: 80 # Minimum f0 for pitch extraction.
|
||||||
|
f0max: 750 # Maximum f0 for pitch extraction.
|
||||||
|
|
||||||
|
|
||||||
|
###########################################################
|
||||||
|
# DATA SETTING #
|
||||||
|
###########################################################
|
||||||
|
batch_size: 32
|
||||||
|
num_workers: 4
|
||||||
|
|
||||||
|
|
||||||
|
###########################################################
|
||||||
|
# MODEL SETTING #
|
||||||
|
###########################################################
|
||||||
|
# fastspeech2 module
|
||||||
|
fs2_model:
|
||||||
|
adim: 256 # attention dimension
|
||||||
|
aheads: 2 # number of attention heads
|
||||||
|
elayers: 4 # number of encoder layers
|
||||||
|
eunits: 1536 # number of encoder ff units
|
||||||
|
dlayers: 4 # number of decoder layers
|
||||||
|
dunits: 1536 # number of decoder ff units
|
||||||
|
positionwise_layer_type: conv1d # type of position-wise layer
|
||||||
|
positionwise_conv_kernel_size: 3 # kernel size of position wise conv layer
|
||||||
|
duration_predictor_layers: 2 # number of layers of duration predictor
|
||||||
|
duration_predictor_chans: 256 # number of channels of duration predictor
|
||||||
|
duration_predictor_kernel_size: 3 # filter size of duration predictor
|
||||||
|
postnet_layers: 5 # number of layers of postnset
|
||||||
|
postnet_filts: 5 # filter size of conv layers in postnet
|
||||||
|
postnet_chans: 256 # number of channels of conv layers in postnet
|
||||||
|
use_scaled_pos_enc: True # whether to use scaled positional encoding
|
||||||
|
encoder_normalize_before: True # whether to perform layer normalization before the input
|
||||||
|
decoder_normalize_before: True # whether to perform layer normalization before the input
|
||||||
|
reduction_factor: 1 # reduction factor
|
||||||
|
init_type: xavier_uniform # initialization type
|
||||||
|
init_enc_alpha: 1.0 # initial value of alpha of encoder scaled position encoding
|
||||||
|
init_dec_alpha: 1.0 # initial value of alpha of decoder scaled position encoding
|
||||||
|
transformer_enc_dropout_rate: 0.2 # dropout rate for transformer encoder layer
|
||||||
|
transformer_enc_positional_dropout_rate: 0.2 # dropout rate for transformer encoder positional encoding
|
||||||
|
transformer_enc_attn_dropout_rate: 0.2 # dropout rate for transformer encoder attention layer
|
||||||
|
transformer_dec_dropout_rate: 0.2 # dropout rate for transformer decoder layer
|
||||||
|
transformer_dec_positional_dropout_rate: 0.2 # dropout rate for transformer decoder positional encoding
|
||||||
|
transformer_dec_attn_dropout_rate: 0.2 # dropout rate for transformer decoder attention layer
|
||||||
|
pitch_predictor_layers: 5 # number of conv layers in pitch predictor
|
||||||
|
pitch_predictor_chans: 256 # number of channels of conv layers in pitch predictor
|
||||||
|
pitch_predictor_kernel_size: 5 # kernel size of conv leyers in pitch predictor
|
||||||
|
pitch_predictor_dropout: 0.5 # dropout rate in pitch predictor
|
||||||
|
pitch_embed_kernel_size: 1 # kernel size of conv embedding layer for pitch
|
||||||
|
pitch_embed_dropout: 0.0 # dropout rate after conv embedding layer for pitch
|
||||||
|
stop_gradient_from_pitch_predictor: True # whether to stop the gradient from pitch predictor to encoder
|
||||||
|
energy_predictor_layers: 2 # number of conv layers in energy predictor
|
||||||
|
energy_predictor_chans: 256 # number of channels of conv layers in energy predictor
|
||||||
|
energy_predictor_kernel_size: 3 # kernel size of conv leyers in energy predictor
|
||||||
|
energy_predictor_dropout: 0.5 # dropout rate in energy predictor
|
||||||
|
energy_embed_kernel_size: 1 # kernel size of conv embedding layer for energy
|
||||||
|
energy_embed_dropout: 0.0 # dropout rate after conv embedding layer for energy
|
||||||
|
stop_gradient_from_energy_predictor: False # whether to stop the gradient from energy predictor to encoder
|
||||||
|
note_num: 300
|
||||||
|
is_slur_num: 2
|
||||||
|
|
||||||
|
denoiser_model:
|
||||||
|
in_channels: 80
|
||||||
|
out_channels: 80
|
||||||
|
kernel_size: 3
|
||||||
|
layers: 20
|
||||||
|
stacks: 4
|
||||||
|
residual_channels: 256
|
||||||
|
gate_channels: 512
|
||||||
|
skip_channels: 256
|
||||||
|
aux_channels: 256
|
||||||
|
dropout: 0.1
|
||||||
|
bias: True
|
||||||
|
use_weight_norm: False
|
||||||
|
init_type: kaiming_uniform
|
||||||
|
|
||||||
|
diffusion:
|
||||||
|
num_train_timesteps: 100
|
||||||
|
beta_start: 0.0001
|
||||||
|
beta_end: 0.06
|
||||||
|
beta_schedule: "squaredcos_cap_v2"
|
||||||
|
num_max_timesteps: 60
|
||||||
|
|
||||||
|
|
||||||
|
###########################################################
|
||||||
|
# UPDATER SETTING #
|
||||||
|
###########################################################
|
||||||
|
fs2_updater:
|
||||||
|
use_masking: True # whether to apply masking for padded part in loss calculation
|
||||||
|
|
||||||
|
ds_updater:
|
||||||
|
use_masking: True # whether to apply masking for padded part in loss calculation
|
||||||
|
|
||||||
|
|
||||||
|
###########################################################
|
||||||
|
# OPTIMIZER SETTING #
|
||||||
|
###########################################################
|
||||||
|
# gpu_num=2 config
|
||||||
|
# fastspeech2 optimizer
|
||||||
|
fs2_optimizer:
|
||||||
|
optim: adam # optimizer type
|
||||||
|
learning_rate: 0.001 # learning rate
|
||||||
|
|
||||||
|
# diffusion optimizer
|
||||||
|
ds_optimizer_params:
|
||||||
|
beta1: 0.9
|
||||||
|
beta2: 0.98
|
||||||
|
weight_decay: 0.0
|
||||||
|
|
||||||
|
ds_scheduler_params:
|
||||||
|
learning_rate: 0.001
|
||||||
|
gamma: 0.5
|
||||||
|
step_size: 25000
|
||||||
|
ds_grad_norm: 1
|
||||||
|
|
||||||
|
|
||||||
|
###########################################################
|
||||||
|
# INTERVAL SETTING #
|
||||||
|
###########################################################
|
||||||
|
ds_train_start_steps: 80000 # Number of steps to start to train diffusion module.
|
||||||
|
train_max_steps: 160000 # Number of training steps.
|
||||||
|
save_interval_steps: 1000 # Interval steps to save checkpoint.
|
||||||
|
eval_interval_steps: 250 # Interval steps to evaluate the network.
|
||||||
|
num_snapshots: 5
|
||||||
|
|
||||||
|
|
||||||
|
###########################################################
|
||||||
|
# OTHER SETTING #
|
||||||
|
###########################################################
|
||||||
|
seed: 10086
|
||||||
|
find_unused_parameters: True
|
||||||
@ -0,0 +1,13 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
export MAIN_ROOT=`realpath ${PWD}/../../../`
|
||||||
|
|
||||||
|
export PATH=${MAIN_ROOT}:${MAIN_ROOT}/utils:${PATH}
|
||||||
|
export LC_ALL=C
|
||||||
|
|
||||||
|
export PYTHONDONTWRITEBYTECODE=1
|
||||||
|
# Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
|
||||||
|
export PYTHONIOENCODING=UTF-8
|
||||||
|
export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH}
|
||||||
|
|
||||||
|
MODEL=diffsinger
|
||||||
|
export BIN_DIR=${MAIN_ROOT}/paddlespeech/t2s/exps/${MODEL}
|
||||||
Loading…
Reference in new issue