Upload new model: french-base-model-french-processed

.gitattributes

@@ -54,3 +54,4 @@ ember-german-v1/0007.wav filter=lfs diff=lfs merge=lfs -text
 german-base-fast/0004.wav filter=lfs diff=lfs merge=lfs -text
 german-base-model/0004.wav filter=lfs diff=lfs merge=lfs -text
 PL-Bert[[:space:]]German/step_1100000.t7 filter=lfs diff=lfs merge=lfs -text
+french-base-model/default.wav filter=lfs diff=lfs merge=lfs -text

french-base-model/config_french_base_full.yml

@@ -0,0 +1,20 @@
+{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: French_Data/OOD_texts.txt,
+    min_length: 50, root_path: /root/src/StyleTTS2/French_Data, train_data: French_Data/french_train_list_cleaned.txt,
+    val_data: French_Data/french_val_list_cleaned.txt}, device: cuda, epochs: 20,
+  load_only_params: true, log_dir: FinetunedModels/french-base-model-full, log_interval: 5,
+  loss_params: {diff_epoch: 6, joint_epoch: 12, 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: 800, 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: 0.15961568889512104, 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: Model/epoch_2nd_00012.pth,
+  save_freq: 5, second_stage_load_pretrained: true, slmadv_params: {batch_percentage: 0.5,
+    iter: 10, max_len: 800, min_len: 640, scale: 0.01, sig: 1.5, thresh: 5}}

french-base-model/default.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6324ad49ac45c25802b0b3c77546c523cdde4281dca90029095647edf9e6a84
+size 202662

french-base-model/epoch_2nd_00019.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a76d37434d9e7a1c04487f3aa23304fe5cd25d4e9b8278a82490088cdfea78
+size 2252234593