Upload folder using huggingface_hub

checkpoint/epoch_2nd_00000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddefc40cb98399391c907a455c9f7916a43a4dc47a19ce14cde654f915968c85
-size 1926290769
+oid sha256:cbc343e4a7795475b6346964c28ee22f97cb023554155ea8c1c1f526b871f89f
+size 1926291032

config_ft.yml

@@ -1,112 +1,21 @@
-log_dir: "Models/LJSpeech"
-save_freq: 1
-log_interval: 10
-device: "cuda"
-epochs: 20 # number of finetuning epoch (1 hour of data)
-batch_size: 2
-max_len: 290 # maximum number of frames
-pretrained_model: "epoch_1st_00000.pth"
-second_stage_load_pretrained: true # set to true if the pre-trained model is for 2nd stage
-load_only_params: false # 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/'
-
-data_params:
-  train_data: "Data/train_list.txt"
-  val_data: "Data/val_list.txt"
-  root_path: "/content/StyleTTS2/Dataset"
-  OOD_data: "Data/OOD_texts.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: 'istftnet' # either hifigan or istftnet
-      resblock_kernel_sizes: [3,7,11]
-      upsample_rates :  [10, 6]
-      gen_istft_hop_size: 5
-      gen_istft_n_fft: 20
-      upsample_initial_channel: 512
-      resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
-      upsample_kernel_sizes: [20, 12]
-      
-  # speech language model config
-  slm:
-      model: 'microsoft/wavlm-base-plus'
-      sr: 16000 # sampling rate of SLM
-      hidden: 768 # hidden size of SLM
-      nlayers: 13 # number of layers of SLM
-      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
-    
-    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: 1000000000000000000000000 # style diffusion starting epoch
-    joint_epoch: 3000000000000000000000000 # joint training starting epoch
-
-optimizer_params:
-  lr: 0.0001 # general learning rate
-  bert_lr: 0.00001 # learning rate for PLBERT
-  ft_lr: 0.0001 # learning rate for acoustic modules
-  
-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: 10 # update the discriminator every this iterations of generator update
-  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
+{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: 2, data_params: {OOD_data: Data/OOD_texts.txt,
+    min_length: 50, root_path: /content/StyleTTS2/Dataset, train_data: Data/train_list.txt,
+    val_data: Data/val_list.txt}, device: cuda, epochs: 20, load_only_params: false,
+  log_dir: Models/LJSpeech, log_interval: 10, loss_params: {diff_epoch: 1000000000000000000000000,
+    joint_epoch: 3000000000000000000000000, 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: 290, model_params: {
+    decoder: {gen_istft_hop_size: 5, gen_istft_n_fft: 20, resblock_dilation_sizes: [
+        [1, 3, 5], [1, 3, 5], [1, 3, 5]], resblock_kernel_sizes: [3, 7, 11], type: istftnet,
+      upsample_initial_channel: 512, upsample_kernel_sizes: [20, 12], upsample_rates: [
+        10, 6]}, diffusion: {dist: {estimate_sigma_data: true, mean: -3.0, sigma_data: .nan,
+        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: 0.0001,
+    lr: 0.0001}, preprocess_params: {spect_params: {hop_length: 300, n_fft: 2048,
+      win_length: 1200}, sr: 24000}, pretrained_model: epoch_1st_00000.pth, save_freq: 1,
+  second_stage_load_pretrained: true, slmadv_params: {batch_percentage: 0.5, iter: 10,
+    max_len: 500, min_len: 400, scale: 0.01, sig: 1.5, thresh: 5}}

epoch_1st_00000.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddefc40cb98399391c907a455c9f7916a43a4dc47a19ce14cde654f915968c85
-size 1926290769
+oid sha256:cbc343e4a7795475b6346964c28ee22f97cb023554155ea8c1c1f526b871f89f
+size 1926291032