Upload 2 files

2nd_phase_last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8375c9224a406cb9c9440feaaf62f3554128b42470ecff75dc78e0beb56a8e4
+size 2044662894

config_kanade_30_epochs.yml

@@ -0,0 +1,118 @@
+log_dir: "Models/LibriTTS-test"
+first_stage_path: "epoch_1st_00040.pth" #This is the path within the models/log_dir, not the relative path from where it's being run. 
+save_freq: 10
+log_interval: 10
+device: "cuda"
+epochs_1st: 50 # number of epochs for first stage training (pre-training)
+epochs_2nd: 30 # number of peochs for second stage training (joint training)
+batch_size: 2
+max_len: 512 # maximum number of frames
+second_stage_load_pretrained: false # 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: "StyleTTS2Utils/JDC/bst.t7"
+ASR_config: "StyleTTS2Utils/ASR/config.yml"
+ASR_path: "StyleTTS2Utils/ASR/epoch_00080.pth"
+PLBERT_dir: 'StyleTTS2Utils/PLBERT/'
+
+
+
+data_params:
+  train_data: data_paths/train_data_filtered.txt
+  val_data: data_paths/val_data_filtered.txt
+  root_path: ""
+  OOD_data: data_paths/ood_data_filtered.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
+
+  decoder: 
+    type: 'istftnet' # either hifigan or istftnet
+    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
+
+
+      
+  # speech language model config
+  slm:
+      model: 'Respair/Whisper_Large_v2_Encoder_Block' # The model itself is hardcoded, change it through -> losses.py
+      sr: 16000 # sampling rate of SLM
+      hidden: 1280 # hidden size of SLM
+      nlayers: 33 # 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: 10. # mel reconstruction loss
+    lambda_gen: 1. # generator loss
+    lambda_slm: 1. # slm feature matching loss
+    
+    lambda_mono: 1. # monotonic alignment loss (1st stage, TMA)
+    lambda_s2s: 1. # sequence-to-sequence loss (1st stage, TMA)
+    TMA_epoch: 5 # TMA starting epoch (1st stage)
+
+    lambda_F0: 1. # F0 reconstruction loss (2nd stage)
+    lambda_norm: 1. # norm reconstruction loss (2nd stage)
+    lambda_dur: 1. # duration loss (2nd stage)
+    lambda_ce: 20. # duration predictor probability output CE loss (2nd stage)
+    lambda_sty: 1. # style reconstruction loss (2nd stage)
+    lambda_diff: 1. # score matching loss (2nd stage)
+    
+    diff_epoch: 4 # style diffusion starting epoch (2nd stage)
+    joint_epoch: 999 # joint training starting epoch (2nd stage)
+
+optimizer_params:
+  lr: 0.00005 # general learning rate
+  bert_lr: 0.00001 # learning rate for PLBERT
+  ft_lr: 0.00001 # 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: 20 # 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