Upload 38 files

.gitattributes

@@ -141,3 +141,21 @@ rvc/voice_models/LainV4/LainIwakura.pth filter=lfs diff=lfs merge=lfs -text
 rvc/voice_models/LainV4/added_IVF240_Flat_nprobe_1_LainIwakura_v2.index filter=lfs diff=lfs merge=lfs -text
 rvc/voice_models/Rick_Sanchez/RickSanchez.index filter=lfs diff=lfs merge=lfs -text
 rvc/voice_models/Rick_Sanchez/RickSanchez_365e_11315s.pth filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/7_12_2048_WavLM/last.ckpt filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/7_12_2048_WavLM/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/9_10_11_12_1024/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/9_12_2048_WavLM/last.ckpt filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/9_12_2048_WavLM/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/KLM-SVM-Embedder_RVC/KLM-SVM.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/KLM-VOCAL-Embedder_RVC/KLM-VOCAL.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/KLM-Vocal-X1/KLM-VOCAL-X1.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/SPIN_450H_FINETUNE_26768/SPIN_450H_FINETUNE_26768_pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/SPIN_450H_FINETUNE_26768/SPIN_450H_FINETUNE_26768.ckpt filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/spin-v2/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/spin/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/spinv2_official/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/spinv2_official/spinv2_epoch=15-step=7216.ckpt filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/wavlm-ft.zip filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/wavLM-SPIN-2048_11_12_updatedConfig/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/wavLM-SPIN-2048_11_12/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+rvc/embedders/custom/WAVLMPLUS-5-12/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

rvc/embedders/custom/7_12_2048_WavLM/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

rvc/embedders/custom/7_12_2048_WavLM/last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3af9b07e24a9bce1d04865eff7d6fb84ef43dd09ac6c0591f0cb996bc304e94
+size 726628553

rvc/embedders/custom/7_12_2048_WavLM/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec8918afd652e4d368fa0199c7f5e7bb58719bbacb7585957d544246d20d877
+size 378356791

rvc/embedders/custom/9_10_11_12_1024/config.json

@@ -0,0 +1,71 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

rvc/embedders/custom/9_10_11_12_1024/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e8082c7eeeb9852c7d72dd3d7d27cef9e476cd9453dbfa19fd89e5ccfb36e9
+size 378356791

rvc/embedders/custom/9_12_2048_WavLM/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

rvc/embedders/custom/9_12_2048_WavLM/last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937ed8aec91711b8074060470c8c15504b02c6200d428df52eac255f8843afe3
+size 613182509

rvc/embedders/custom/9_12_2048_WavLM/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f18898ec10d1f01ba2bd43565be3704f68a8c1c399a6d577dacf46d9c8eef0c
+size 378356791

rvc/embedders/custom/KLM-SVM-Embedder_RVC/KLM-SVM.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358a41c122828ed7dc82fb7449c55309031fc29d9d5af2e975de914ea021d994
+size 378346807

rvc/embedders/custom/KLM-SVM-Embedder_RVC/config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "D:\\Codex\\klm-trainer\\engine\\rvc\\models\\embedders\\contentvec",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

rvc/embedders/custom/KLM-VOCAL-Embedder_RVC/KLM-VOCAL.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b1391ea0370f1cc345fbb404d00afba5f86d869ef1c18e84b9b1cd8a5852d5
+size 378346807

rvc/embedders/custom/KLM-VOCAL-Embedder_RVC/config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "D:\\Codex\\klm-trainer\\engine\\rvc\\models\\embedders\\contentvec",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

rvc/embedders/custom/KLM-Vocal-X1/KLM-VOCAL-X1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c81d1f004c5567441f39b09ed58899066af6ba4439b48b33521ad2e12e7360b
+size 378399563

rvc/embedders/custom/KLM-Vocal-X1/config.json

@@ -0,0 +1,122 @@
+{
+  "_name_or_path": "D:\\Codex\\KLM-HF_V044\\engine\\rvc\\models\\embedders\\wavlm_base_plus",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "WavLMModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "replace_prob": 0.5,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

rvc/embedders/custom/SPIN_450H_FINETUNE_26768/SPIN_450H_FINETUNE_26768.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ebed0cf9316a4cbbeae9e3b2661fb01621d7d6ebe0a6c2898a2e72823042ed
+size 500185456

rvc/embedders/custom/SPIN_450H_FINETUNE_26768/SPIN_450H_FINETUNE_26768_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2980f97e9b6ca0bf2d12afabf2f2643f7408991081ed34df58bd4af1da956c08
+size 378356318

rvc/embedders/custom/SPIN_450H_FINETUNE_26768/config.json

@@ -0,0 +1,71 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

rvc/embedders/custom/SPIN_450H_FINETUNE_26768/spin.yaml

@@ -0,0 +1,91 @@
+# Interspeech 2023 version
+
+# Training data
+data:
+  json_dir: YOUR DATA FOLDER
+  splits:
+    - train-clean-100
+    - train-clean-360
+  sample_rate: 16000
+  min_audio_len: 40000  # minimum audio samples per utterance
+  random_crop_len: 272000  # maximum audio samples per utterance
+  spk2info: YOUR SPK2INFO FILE
+
+# Validation data (not used for checkpointing, just for monitoring training progress)
+val_data:
+  json_dir: YOUR DATA FOLDER
+  phn_dir: YOUR DATA FOLDER
+  splits:
+    - dev-clean
+    - dev-other
+  sample_rate: 16000
+
+# SpinModel config
+model:
+  encoder:
+    type: HuBERT  # `HuBERT` / `WavLM`
+    use_layer: 12  # the layer which its representations are used for clustering
+    normalize: False
+    feat_select: x
+    randomize_all: False
+    randomize_layers: []
+    freeze_all: False
+    freeze_layers: ["pos", 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]  # `pos`: positional encoding, `0`: CNN extractor
+  pred_head:
+    type: DNN
+    hid_dims: [256]
+    dropout: 0
+    activation: ReLU
+  loss:
+    type: SwavVQDisentangle
+    num_vars: 2048  # cluster size
+    epsilon: 0.02
+    sinkhorn_iters: 3
+    temp: 0.1
+    l2_norm: True
+    prob_ratio: 1.0
+
+# Optimization
+optim:
+  optimizer:
+    name: Adam
+    args:
+      lr: 1.e-4
+      weight_decay: 1.e-6
+  scheduler:
+    name: linear_warmup_decay  # `linear_warmup_decay` / `linear_warmup_cosine_scheduler` / `noam_scheduler`
+    args:
+      warmup: 8365 # 1/4th the epochs
+      max_step: 33460 #5e
+      final_lr: 1.e-6
+
+hparam:
+  batch_len: 4096000  # audio samples per GPU (256 secs ~ batch_size = 12.8k)
+  val_batch_size: 8
+
+# pytorch_lightning.Trainer
+# ref: https://lightning.ai/docs/pytorch/latest/common/trainer.html
+trainer:
+  max_steps: 33460 #5e
+  gradient_clip_val: 10
+  accumulate_grad_batches: 1
+  precision: 16
+  logger: wandb  # use `False` to disable logging
+  log_every_n_steps: 100
+  default_root_dir: exp/tmp
+  accelerator: gpu
+  # strategy: ddp  # uncomment this line to enable DDP training
+  num_sanity_val_steps: 0
+  val_check_interval: 1000
+
+# pytorch_lightning.callbacks.ModelCheckpoint
+# ref: https://lightning.ai/docs/pytorch/latest/api/lightning.pytorch.callbacks.ModelCheckpoint.html
+checkpoint:
+  filename: "{epoch}-{step}"
+  every_n_train_steps: 6692 # This is 1 epoch for new set
+  save_last: true
+
+# pytorch_lightning.loggers.WandbLogger
+# ref: https://lightning.ai/docs/pytorch/latest/extensions/generated/lightning.pytorch.loggers.WandbLogger.html
+logger:
+  project: spin_is2023

rvc/embedders/custom/WAVLMPLUS-5-12/config.json

@@ -0,0 +1,99 @@
+{
+  "_name_or_path": "wavlm-base-plus",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "WavLMModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wavlm",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "replace_prob": 0.5,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer"
+}

rvc/embedders/custom/WAVLMPLUS-5-12/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

rvc/embedders/custom/WAVLMPLUS-5-12/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f45914d34b60b82127bf5b4b2ab2600f3796c493cc671c6333458002d409da
+size 378356791

rvc/embedders/custom/spin-v2/config.json

@@ -0,0 +1,72 @@
+{
+    "activation_dropout": 0.1,
+    "apply_spec_augment": true,
+    "architectures": [
+        "HubertModelWithFinalProj"
+    ],
+    "attention_dropout": 0.1,
+    "bos_token_id": 1,
+    "classifier_proj_size": 256,
+    "conv_bias": false,
+    "conv_dim": [
+        512,
+        512,
+        512,
+        512,
+        512,
+        512,
+        512
+    ],
+    "conv_kernel": [
+        10,
+        3,
+        3,
+        3,
+        3,
+        2,
+        2
+    ],
+    "conv_pos_batch_norm": false,
+    "conv_stride": [
+        5,
+        2,
+        2,
+        2,
+        2,
+        2,
+        2
+    ],
+    "ctc_loss_reduction": "sum",
+    "ctc_zero_infinity": false,
+    "do_stable_layer_norm": false,
+    "eos_token_id": 2,
+    "feat_extract_activation": "gelu",
+    "feat_extract_norm": "group",
+    "feat_proj_dropout": 0.0,
+    "feat_proj_layer_norm": true,
+    "final_dropout": 0.1,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.1,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.05,
+    "model_type": "hubert",
+    "num_attention_heads": 12,
+    "num_conv_pos_embedding_groups": 16,
+    "num_conv_pos_embeddings": 128,
+    "num_feat_extract_layers": 7,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "torch_dtype": "float32",
+    "transformers_version": "4.55.0",
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32
+}

rvc/embedders/custom/spin-v2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9ac0be326057b17607a988be497793817f8274e987cf691a1b61192510f823
+size 378356791

rvc/embedders/custom/spin/config.json

@@ -0,0 +1,71 @@
+{
+    "activation_dropout": 0.1,
+    "apply_spec_augment": true,
+    "architectures": [
+        "HubertModelWithFinalProj"
+    ],
+    "attention_dropout": 0.1,
+    "bos_token_id": 1,
+    "classifier_proj_size": 256,
+    "conv_bias": false,
+    "conv_dim": [
+        512,
+        512,
+        512,
+        512,
+        512,
+        512,
+        512
+    ],
+    "conv_kernel": [
+        10,
+        3,
+        3,
+        3,
+        3,
+        2,
+        2
+    ],
+    "conv_stride": [
+        5,
+        2,
+        2,
+        2,
+        2,
+        2,
+        2
+    ],
+    "ctc_loss_reduction": "sum",
+    "ctc_zero_infinity": false,
+    "do_stable_layer_norm": false,
+    "eos_token_id": 2,
+    "feat_extract_activation": "gelu",
+    "feat_extract_norm": "group",
+    "feat_proj_dropout": 0.0,
+    "feat_proj_layer_norm": true,
+    "final_dropout": 0.1,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.1,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.05,
+    "model_type": "hubert",
+    "num_attention_heads": 12,
+    "num_conv_pos_embedding_groups": 16,
+    "num_conv_pos_embeddings": 128,
+    "num_feat_extract_layers": 7,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "torch_dtype": "float32",
+    "transformers_version": "4.44.2",
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32
+}

rvc/embedders/custom/spin/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057f12bfda54e2d486d86a52a3beb2a07c96a888bc6ac0c382c12ac18dbd500c
+size 378356791

rvc/embedders/custom/spinv2_official/config.json

@@ -0,0 +1,72 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

rvc/embedders/custom/spinv2_official/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9ac0be326057b17607a988be497793817f8274e987cf691a1b61192510f823
+size 378356791

rvc/embedders/custom/spinv2_official/spinv2_epoch=15-step=7216.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0344e316aee5a2b63dcb2de643d686271974b5bc523dfdc74c8fc079e79765
+size 837338557

rvc/embedders/custom/wavLM-SPIN-2048_11_12/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

rvc/embedders/custom/wavLM-SPIN-2048_11_12/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978162a5049473a8f9d0b4ddc5d98d229c08b5c32040e0888fe275099515a0eb
+size 378356791

rvc/embedders/custom/wavLM-SPIN-2048_11_12_updatedConfig/config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

rvc/embedders/custom/wavLM-SPIN-2048_11_12_updatedConfig/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978162a5049473a8f9d0b4ddc5d98d229c08b5c32040e0888fe275099515a0eb
+size 378356791

rvc/embedders/custom/wavlm-ft.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bab5e063c0d987821b0c323af4c86d656382b8a6e127f6d637000b29d2a55e3
+size 298471330