Update config.yml

config.yml

@@ -1,21 +1,111 @@
-{ASR_config: Utils/ASR/config.yml, ASR_path: Utils/ASR/epoch_00080.pth, F0_path: Utils/JDC/bst.t7,
-  PLBERT_dir: Utils/PLBERT/, batch_size: 8, data_params: {OOD_data: Data/OOD_texts.txt,
-    min_length: 50, root_path: '', train_data: Data/train_list.txt, val_data: Data/val_list.txt},
-  device: cuda, epochs_1st: 40, epochs_2nd: 25, first_stage_path: first_stage.pth,
-  load_only_params: false, log_dir: Models/LibriTTS, log_interval: 10, loss_params: {
-    TMA_epoch: 4, diff_epoch: 0, joint_epoch: 0, lambda_F0: 1.0, lambda_ce: 20.0,
-    lambda_diff: 1.0, lambda_dur: 1.0, lambda_gen: 1.0, lambda_mel: 5.0, lambda_mono: 1.0,
-    lambda_norm: 1.0, lambda_s2s: 1.0, lambda_slm: 1.0, lambda_sty: 1.0}, max_len: 300,
-  model_params: {decoder: {resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3,
-          5]], resblock_kernel_sizes: [3, 7, 11], type: hifigan, upsample_initial_channel: 512,
-      upsample_kernel_sizes: [20, 10, 6, 4], upsample_rates: [10, 5, 3, 2]}, diffusion: {
-      dist: {estimate_sigma_data: true, mean: -3.0, sigma_data: 0.19926648961191362,
-        std: 1.0}, embedding_mask_proba: 0.1, transformer: {head_features: 64, multiplier: 2,
-        num_heads: 8, num_layers: 3}}, dim_in: 64, dropout: 0.2, hidden_dim: 512,
-    max_conv_dim: 512, max_dur: 50, multispeaker: true, n_layer: 3, n_mels: 80, n_token: 178,
-    slm: {hidden: 768, initial_channel: 64, model: microsoft/wavlm-base-plus, nlayers: 13,
-      sr: 16000}, style_dim: 128}, optimizer_params: {bert_lr: 1.0e-05, ft_lr: 1.0e-05,
-    lr: 0.0001}, preprocess_params: {spect_params: {hop_length: 300, n_fft: 2048,
-      win_length: 1200}, sr: 24000}, pretrained_model: Models/LibriTTS/epoch_2nd_00002.pth,
-  save_freq: 1, second_stage_load_pretrained: true, slmadv_params: {batch_percentage: 0.5,
-    iter: 20, max_len: 500, min_len: 400, scale: 0.01, sig: 1.5, thresh: 5}}
+log_dir: "Models/0413-english-39k"
+save_freq: 1
+log_interval: 10
+device: "cuda"
+epochs: 30 # number of finetuning epoch
+batch_size: 8
+max_len: 400 # maximum number of frames
+pretrained_model: "Models/LibriTTS/epochs_2nd_00020.pth" #Models/LibriTTS/epochs_2nd_00020.pth
+second_stage_load_pretrained: true # set to true if the pre-trained model is for 2nd stage
+load_only_params: true # set to true if do not want to load epoch numbers and optimizer parameters
+
+F0_path: "Utils/JDC/bst.t7"
+ASR_config: "Utils/ASR/config.yml"
+ASR_path: "Utils/ASR/epoch_00080.pth"
+PLBERT_dir: 'Utils/PLBERT' #Utils/PLBERT、Utils/PLBERT_all_languages
+
+data_params:
+  train_data: "/workspace/TTS/tts/StyleTTS2/Data/train_list_en_39k_0413.txt"
+  val_data: "/workspace/TTS/tts/StyleTTS2/Data/val_list_en_21k_0401.txt"
+  root_path: ""
+  OOD_data: "/workspace/TTS/tts/StyleTTS2/Data/OOD_texts_en_7k_0413.txt"
+  min_length: 50 # sample until texts with this size are obtained for OOD texts
+
+preprocess_params:
+  sr: 24000
+  spect_params:
+    n_fft: 2048
+    win_length: 1200
+    hop_length: 300
+
+model_params:
+  multispeaker: true
+
+  dim_in: 64 
+  hidden_dim: 512
+  max_conv_dim: 512
+  n_layer: 3
+  n_mels: 80
+
+  n_token: 178 # number of phoneme tokens
+  max_dur: 50 # maximum duration of a single phoneme
+  style_dim: 128 # style vector size
+  
+  dropout: 0.2
+
+  # config for decoder
+  decoder: 
+      type: 'hifigan' # either hifigan or istftnet
+      resblock_kernel_sizes: [3,7,11]
+      upsample_rates :  [10,5,3,2]
+      upsample_initial_channel: 512
+      resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
+      upsample_kernel_sizes: [20,10,6,4]
+      
+  # speech language model config
+  slm:
+      model: 'microsoft/wavlm-base-plus' # microsoft/wavlm-base-plus, facebook/wav2vec2-large-xlsr-53
+      sr: 16000 # sampling rate of SLM
+      hidden: 768 # hidden size of SLM，本来为768，xlsr为1024
+      nlayers: 13 # number of layers of SLM，本来为13，xlsr为25
+      initial_channel: 64 # initial channels of SLM discriminator head
+  
+  # style diffusion model config
+  diffusion:
+    embedding_mask_proba: 0.1
+    # transformer config
+    transformer:
+      num_layers: 3
+      num_heads: 8
+      head_features: 64
+      multiplier: 2
+
+    # diffusion distribution config
+    dist:
+      sigma_data: 0.2 # placeholder for estimate_sigma_data set to false
+      estimate_sigma_data: true # estimate sigma_data from the current batch if set to true
+      mean: -3.0
+      std: 1.0
+  
+loss_params:
+    lambda_mel: 5. # mel reconstruction loss
+    lambda_gen: 1. # generator loss
+    lambda_slm: 1. # slm feature matching loss，本来为1
+    
+    lambda_mono: 1. # monotonic alignment loss (TMA)
+    lambda_s2s: 1. # sequence-to-sequence loss (TMA)
+
+    lambda_F0: 1. # F0 reconstruction loss
+    lambda_norm: 1. # norm reconstruction loss
+    lambda_dur: 1. # duration loss
+    lambda_ce: 20. # duration predictor probability output CE loss
+    lambda_sty: 1. # style reconstruction loss
+    lambda_diff: 1. # score matching loss
+    
+    diff_epoch: 2 # style diffusion starting epoch
+    joint_epoch: 4 # joint training starting epoch
+
+optimizer_params:
+  lr: 0.00005 # general learning rate，原本为0.0001
+  bert_lr: 0.000005 # learning rate for PLBERT，原本为0.00001
+  ft_lr: 0.000005 # learning rate for acoustic modules，原本为0.0001,libritts为0.00001
+  
+slmadv_params:
+  min_len: 400 # minimum length of samples
+  max_len: 500 # maximum length of samples
+  batch_percentage: 0.5 # to prevent out of memory, only use half of the original batch size
+  iter: 20 # update the discriminator every this iterations of generator update，libritts为20
+  thresh: 5 # gradient norm above which the gradient is scaled
+  scale: 0.01 # gradient scaling factor for predictors from SLM discriminators
+  sig: 1.5 # sigma for differentiable duration modeling
+