Upload folder using huggingface_hub

100_forget_egu/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/100_forget_speakers/train/ref_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/100_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 10,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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: 400,
+  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: 0.20376779402419926,
+        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: Models/LibriTTS/epochs_2nd_00020.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}, wandb: {
+    enable: true}}

100_forget_egu/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2469305dd910892da9561a331918f8bdc29e4815d70320a46fdba47786ff95
+size 969282062

100_forget_egu_triplet/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/100_forget_speakers/train/ref_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/100_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 15,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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, lambda_triplet: 1.0,
+    margin: 0.3}, max_len: 400, 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: 0.20375831651041906,
+        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: Models/LibriTTS/epochs_2nd_00020.pth,
+  save_freq: 5, 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}, wandb: {
+    enable: true}}

100_forget_egu_triplet/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229db2de4db3dbf9866bab2fd476a9cc5ae4485177fcfd3a18143d97afb234b9
+size 969282062

100_forget_tgu/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/100_forget_speakers/train/diffusion_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/100_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 10,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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: 400,
+  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: 0.15697235249678293,
+        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: Models/LibriTTS/epochs_2nd_00020.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}, wandb: {
+    enable: true}}

100_forget_tgu/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbe9761a9f41418b91df39b60a5a7142a2516d0ea63ba5168ddc66699622690
+size 969282062

100_forget_tgu_triplet/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/100_forget_speakers/train/diffusion_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/100_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 15,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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, lambda_triplet: 1.0,
+    margin: 0.3}, max_len: 400, 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: 0.156894940473636,
+        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: Models/LibriTTS/epochs_2nd_00020.pth,
+  save_freq: 5, 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}, wandb: {
+    enable: true}}

100_forget_tgu_triplet/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2d1c1bc517923fec2bd7fe1ed7055be3886888db2c046905a426e1ff904439
+size 969282062

15_forget_egu/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/15_forget_speakers/train/ref_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/15_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 10,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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: 400,
+  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: 0.2037010099803408,
+        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: Models/LibriTTS/epochs_2nd_00020.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}, wandb: {
+    enable: true}}

15_forget_egu/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d97c9969381a5c077b79fc3bf806cee8315e67ca7e7ee0c59c81e837c337e7
+size 969282062

15_forget_egu_triplet/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/15_forget_speakers/train/ref_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/15_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 15,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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, lambda_triplet: 1.0,
+    margin: 0.3}, max_len: 400, 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: 0.20370513431802392,
+        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: Models/LibriTTS/epochs_2nd_00020.pth,
+  save_freq: 5, 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}, wandb: {
+    enable: true}}

15_forget_egu_triplet/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b50f6478269b779c3b214c37e11fdf2d48282ba440930747254f0f2c1b665c
+size 969282062

15_forget_tgu/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/15_forget_speakers/train/diffusion_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/15_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 10,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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: 400,
+  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: 0.1566601270151635,
+        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: Models/LibriTTS/epochs_2nd_00020.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}, wandb: {
+    enable: true}}

15_forget_tgu/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497116823ef4207915e7a2a0383ca225910f7d339dfc800ab4f3b175fee9895c
+size 969282062

15_forget_tgu_triplet/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/15_forget_speakers/train/diffusion_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/15_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 15,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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, lambda_triplet: 1.0,
+    margin: 0.3}, max_len: 400, 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: 0.1568964134628574,
+        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: Models/LibriTTS/epochs_2nd_00020.pth,
+  save_freq: 5, 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}, wandb: {
+    enable: true}}

15_forget_tgu_triplet/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dea6b8a84771a0ea0a339c69ed196605afcf7ecfe04c66d4fc9fe53fdcfef1
+size 969282062

1_forget_egu/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/1_forget_speakers/train/ref_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/1_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 10,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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: 400,
+  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: 0.20370649736846486,
+        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: Models/LibriTTS/epochs_2nd_00020.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}, wandb: {
+    enable: true}}

1_forget_egu/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6101c6ade4758837187d6a7ea40747cd40067264c3559d6756f835a1cd1a0dd
+size 969282062

1_forget_egu_triplet/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/1_forget_speakers/train/ref_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/1_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 15,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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, lambda_triplet: 1.0,
+    margin: 0.3}, max_len: 400, 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: 0.20370074871083102,
+        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: Models/LibriTTS/epochs_2nd_00020.pth,
+  save_freq: 5, 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}, wandb: {
+    enable: true}}

1_forget_egu_triplet/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28b76c757efa45a41dad572d16e0e0d18c58d0f412613896b07a1e0e4617fb1
+size 969282062

1_forget_tgu/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/1_forget_speakers/train/diffusion_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/1_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 10,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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: 400,
+  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: 0.15658384388759733,
+        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: Models/LibriTTS/epochs_2nd_00020.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}, wandb: {
+    enable: true}}

1_forget_tgu/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c48f8f91f1e8cec34a06d4b9035520ee4050450526c5b6294b53d8f12bda890b
+size 969282062

1_forget_tgu_triplet/config.yml

@@ -0,0 +1,24 @@
+{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: 32, data_params: {OOD_data: Data/OOD_texts.txt,
+    dataset_path: Unlearning/LibriTTS/1_forget_speakers/train/diffusion_data.csv,
+    forget_ratio: 0.5, forget_speaker_file: Unlearning/LibriTTS/1_forget_speakers/train/forget_speaker_train.csv,
+    min_length: 50, num_workers: 2, root_path: /local/LJSpeech-1.1/wavs, test_size: 0.05,
+    train_data: Data/train_list.txt, val_data: Data/val_list.txt}, device: cuda, epochs: 15,
+  load_only_params: true, log_dir: Unlearning/Models/Unlearning,
+  log_interval: 10, loss_params: {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, lambda_triplet: 1.0,
+    margin: 0.3}, max_len: 400, 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: 0.1569021674056848,
+        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: Models/LibriTTS/epochs_2nd_00020.pth,
+  save_freq: 5, 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}, wandb: {
+    enable: true}}

1_forget_tgu_triplet/last.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e95a71004c79c762937705679b5baa77b0d11954800e1dc069b3eec47db6e4d
+size 969282062

pretrained/config.yml

@@ -0,0 +1,21 @@
+{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}}

pretrained/epochs_2nd_00020.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1164ffe19a17449d2c722234cecaf2836b35a698fb8ffd42562d2663657dca0a
+size 771390526