add pretrained models

configs/tts_infer.yaml

@@ -0,0 +1,9 @@
+default_v2:
+  bert_base_path: pretrained_models/chinese-roberta-wwm-ext-large
+  cnhuhbert_base_path: pretrained_models/chinese-hubert-base
+  device: cpu
+  is_half: false
+  t2s_weights_path: pretrained_models/s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt
+  version: v2
+  vits_config_path: pretrained_models/s2_config.json
+  vits_weights_path: pretrained_models/s2G2333k.pth

pretrained_models/chinese-hubert-base/config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "/data/docker/liujing04/gpt-vits/chinese-hubert-base",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "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": "float16",
+  "transformers_version": "4.30.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

pretrained_models/chinese-hubert-base/preprocessor_config.json

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

pretrained_models/chinese-hubert-base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24164f129c66499d1346e2aa55f183250c223161ec2770c0da3d3b08cf432d3c
+size 188811417

pretrained_models/chinese-roberta-wwm-ext-large/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/data/docker/liujing04/bert-vits2/Bert-VITS2-master20231106/bert/chinese-roberta-wwm-ext-large",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

pretrained_models/chinese-roberta-wwm-ext-large/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53a693acc59ace251d143d068096ae0d7b79e4b1b503fa84c9dcf576448c1d8
+size 651225145

pretrained_models/s1bert25hz-5kh-longer-epoch=12-step=369668.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732f94e63b148066e24c7f9d2637f3374083e637635f07fbdb695dee20ddbe1f
+size 155315150

pretrained_models/s2D2333k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae7fe8dd8c8f2e718de359e00edac88b0c71ab2fd10b07ad4cc45070eb8a836
+size 93534164

pretrained_models/s2G2333k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924fdccaa3c574bf139c25c9759aa1ed3b3f99e19a7c529ee996c2bc17663695
+size 106035259

pretrained_models/s2_config.json

@@ -0,0 +1,101 @@
+{
+    "train": {
+        "log_interval": 100,
+        "eval_interval": 500,
+        "seed": 1234,
+        "epochs": 8,
+        "learning_rate": 0.0001,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 11,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 20480,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0,
+        "text_low_lr_rate": 0.4,
+        "pretrained_s2G": "pretrained_models/s2G2333k.pth",
+        "pretrained_s2D": "pretrained_models/s2D2333k.pth",
+        "if_save_latest": true,
+        "if_save_every_weights": true,
+        "save_every_epoch": 4,
+        "gpu_numbers": "0"
+    },
+    "data": {
+        "max_wav_value": 32768.0,
+        "sampling_rate": 32000,
+        "filter_length": 2048,
+        "hop_length": 640,
+        "win_length": 2048,
+        "n_mel_channels": 128,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 300,
+        "cleaned_text": true,
+        "exp_dir": "logs/s2"
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            10,
+            8,
+            2,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            8,
+            2,
+            2
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false,
+        "gin_channels": 512,
+        "semantic_frame_rate": "25hz",
+        "freeze_quantizer": true,
+        "version": "v2"
+    },
+    "s2_ckpt_dir": "logs/s2/big2k1",
+    "content_module": "cnhubert",
+    "save_weight_dir": "SoVITS_weights_v2",
+    "name": "big2k1",
+    "version": "v2"
+}