-
Notifications
You must be signed in to change notification settings - Fork 659
Description
log_dir: "Models/Hindi"
first_stage_path: "first_stage.pth"
save_freq: 2
log_interval: 10
device: "cuda:0"
epochs_1st: 200 # first stage training
epochs_2nd: 100 # second stage (joint training)
batch_size: 16
max_len: 400 # maximum number of frames
pretrained_model: ""
second_stage_load_pretrained: true
load_only_params: false
F0_path: "Utils/JDC/bst.t7"
ASR_config: "Utils/ASR/config.yml"
ASR_path: "Utils/ASR/epoch_00080.pth"
PLBERT_dir: "Utils/PLBERT/"
data_params:
train_data: "/home/anuragmishra/Anurag/TTS/Training_TTS/StyleTTS/StyleTTS2/Data/train_list.txt"
val_data: "/home/anuragmishra/Anurag/TTS/Training_TTS/StyleTTS/StyleTTS2/Data/val_list.txt"
root_path: "/home/anuragmishra/Anurag/TTS/Training_TTS/StyleTTS/StyleTTS2/Data/Hindi/wavs_clean"
OOD_data: "/home/anuragmishra/Anurag/TTS/Training_TTS/StyleTTS/StyleTTS2/Data/Hindi_ODD.txt"
min_length: 50
preprocess_params:
sr: 24000
spect_params:
n_fft: 2048
win_length: 1200
hop_length: 300
model_params:
multispeaker: false
dim_in: 64
hidden_dim: 512
max_conv_dim: 512
n_layer: 3
n_mels: 80
n_token: 178
max_dur: 50
style_dim: 128
dropout: 0.2
decoder:
type: "istftnet" # or hifigan
resblock_kernel_sizes: [3,7,11]
upsample_rates: [10,6]
upsample_initial_channel: 512
resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
upsample_kernel_sizes: [20,12]
gen_istft_n_fft: 20
gen_istft_hop_size: 5
slm:
model: "microsoft/wavlm-base-plus"
sr: 16000
hidden: 768
nlayers: 13
initial_channel: 64
diffusion:
embedding_mask_proba: 0.1
transformer:
num_layers: 3
num_heads: 8
head_features: 64
multiplier: 2
dist:
sigma_data: 0.2
estimate_sigma_data: true
mean: -3.0
std: 1.0
loss_params:
lambda_mel: 5.0
lambda_gen: 1.0
lambda_slm: 1.0
lambda_mono: 1.0
lambda_s2s: 1.0
TMA_epoch: 50
lambda_F0: 1.0
lambda_norm: 1.0
lambda_dur: 1.0
lambda_ce: 20.0
lambda_sty: 1.0
lambda_diff: 1.0
diff_epoch: 20
joint_epoch: 50
optimizer_params:
lr: 0.0001
bert_lr: 0.00001
ft_lr: 0.00001
slmadv_params:
min_len: 400
max_len: 500
batch_percentage: 0.5
iter: 10
thresh: 5
scale: 0.01
sig: 1.5
this is my config i am unable to understand the issue