GPTSoVITS pretrained model

GPT_SoVITS/pretrained_models/.gitignore

@@ -1,2 +0,0 @@
-*
-!.gitignore

GPT_SoVITS/pretrained_models/README.md

@@ -0,0 +1,4 @@
+---
+license: mit
+---
+pretrained models used in https://github.com/RVC-Boss/GPT-SoVITS

GPT_SoVITS/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
+}

GPT_SoVITS/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
+}

GPT_SoVITS/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

GPT_SoVITS/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
+}

GPT_SoVITS/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

GPT_SoVITS/pretrained_models/s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c1e17e9c99547a89388f72048cd6e1b41b5a18b170e86a46dfde0324d63eb1
+size 155093966

GPT_SoVITS/pretrained_models/s2D488k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc579c1db3c1e21b721001cf99d7a584214280df19b002e200b630a34fa06eb8
+size 93533667

GPT_SoVITS/pretrained_models/s2G488k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020a014e1e01e550e510f2f61fae5e5f5b6aab40f15c22f1f12f724df507e835
+size 105973721

GPT_SoVITS/pretrained_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch

@@ -0,0 +1 @@
+Subproject commit 0dc8a78103e8c28bc6ddbc5352420178f961f9e9