Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.dict filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+license: mit
+language:
+- ja
+- zh
+- ko
+- en
+base_model:
+- lj1995/GPT-SoVITS
+pipeline_tag: text-to-speech
+---
+Look at: https://github.com/neodyland/gpt-sovits-v2-pro-simple

chinese-hubert-base/config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "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
+}

chinese-hubert-base/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f323dd2c87570864910fe48a21222a894dfb9200a2a5e243f43dde1b1b20b8
+size 188767008

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

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "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
+}

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

dict/cmudict.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6aa06b6e2ce28181623ac59f7be7a7b154b0bd23dd0b1e0db634e64196545d0
+size 4157837

dict/ja.dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44817ce96e24be7bcfdd009d834b5237fe044dc9ed5f2f9709f71da9d506fed
+size 21321666

dict/opencpop-strict.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f469a624aa8726cd0e34eb5985f3c82ea7552550b3d07971602d2a975888021
+size 4516

dict/polyphonic.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e65b6be61bfa5e6a5c7435276a7057ad6d54e6c67bca0e8ecfb32b71c3c994
+size 1203541

fast_langdetect/lid.176.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e69ec5451bc261cc7844e49e4792a85d7f09c06789ec800fc4a44aec362764e
+size 131266198

g2pw_model/bopomofo_to_pinyin_wo_tune_dict.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5adf0b644d95f9f5335f4d2976f7f7ffd0874f4c9f3bb0eeeda2557a10c59632
+size 5198

g2pw_model/char2phonemes.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e96db6363efc97dcbf24cfaa0e301f358730b9b9dea8eb64ff4ea076ab4f88
+size 39732

g2pw_model/char_bopomofo_dict.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985a38e7a663cb854246abcd839b08a5c77453916781b0a67c881e05f7fc32dd
+size 687053

g2pw_model/labels.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3b8a266b2bc91b9a68c41b24aa77f602c204a6a7478d0ef7e0db4b444ff50a
+size 11697

g2pw_model/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bee7f91aaa0dbcd0d61d0bce0ede36b68952de4c6b5d4319a8c949b6d654c70
+size 635213222

g2pw_model/monophonic_chars_dict.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea810e70723937971df2d77f92aa110111426ab69d60ff3d510e875a2cdb4aa
+size 120747

gsv/config.json

@@ -0,0 +1,38 @@
+{
+    "train": {
+        "seed": 1234,
+        "epochs": 200,
+        "batch_size": 5,
+        "save_every_n_epoch": 1,
+        "precision": "16-mixed",
+        "gradient_clip": 1.0
+    },
+    "optimizer": {
+        "lr": 0.01,
+        "lr_init": 1e-05,
+        "lr_end": 0.0001,
+        "warmup_steps": 2000,
+        "decay_steps": 40000
+    },
+    "data": {
+        "max_eval_sample": 8,
+        "max_sec": 57,
+        "num_workers": 4,
+        "pad_val": 1024
+    },
+    "model": {
+        "vocab_size": 1025,
+        "phoneme_vocab_size": 732,
+        "embedding_dim": 512,
+        "hidden_dim": 512,
+        "head": 16,
+        "linear_units": 2048,
+        "n_layer": 24,
+        "dropout": 0,
+        "EOS": 1024,
+        "random_bert": 0
+    },
+    "inference": {
+        "top_k": 5
+    }
+}

gsv/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3e6a748c2cac88e637d4059a9b1a70e3d9b5f808185fb66c30818299487082
+size 155240396

sv/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a55b64a81b035db936a7508df4b7e86133738b76fa272e86fd05711630fa0c
+size 91546698

v2pro/v2pro.json

@@ -0,0 +1,56 @@
+{
+    "data": {
+        "sampling_rate": 32000,
+        "filter_length": 2048,
+        "hop_length": 640,
+        "win_length": 2048
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.0,
+        "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
+        ],
+        "gin_channels": 1024
+    }
+}

v2pro/v2pro.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e23be437cacee6846c545e533f42ea9f3ce72baa6fafb38ee21dd81e28bdd2
+size 133220264

v2pro/v2proplus.json

@@ -0,0 +1,56 @@
+{
+    "data": {
+        "sampling_rate": 32000,
+        "filter_length": 2048,
+        "hop_length": 640,
+        "win_length": 2048
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.0,
+        "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": 768,
+        "upsample_kernel_sizes": [
+            20,
+            16,
+            8,
+            2,
+            2
+        ],
+        "gin_channels": 1024
+    }
+}

v2pro/v2proplus.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229b8a25376a7bf3ce2e4fc6c49c04982b4c40bb5496999782a78e76c4577707
+size 171041248