Upload folder using huggingface_hub

Browse files

Files changed (10) hide show

bert_zh/special_tokens_map.json +37 -0
bert_zh/tokenizer.json +0 -0
bert_zh/tokenizer_config.json +62 -0
bert_zh/vocab.txt +0 -0
config.json +192 -0
onnx/model.onnx +3 -0
preprocessor_config.json +6 -0
special_tokens_map.json +16 -0
tokenizer_config.json +38 -0
vocab.json +114 -0

bert_zh/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

bert_zh/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

bert_zh/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,62 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": null,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

bert_zh/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

config.json ADDED Viewed

	@@ -0,0 +1,192 @@

+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "../../ellie-BertVITS2-mini",
+  "activation_dropout": 0.1,
+  "architectures": [
+    "BertVits2Model"
+  ],
+  "attention_dropout": 0.1,
+  "auto_map": {
+    "AutoConfig": "BricksDisplay/ellie-Bert-VITS2--configuration_bert_vits2.BertVits2Config",
+    "AutoModel": "BricksDisplay/ellie-Bert-VITS2--modeling_bert_vits2.BertVits2Model"
+  },
+  "bert_configs": [
+    {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "distilbert-base-multilingual-cased",
+      "activation": "gelu",
+      "add_cross_attention": false,
+      "architectures": [
+        "DistilBertForMaskedLM"
+      ],
+      "attention_dropout": 0.1,
+      "attention_probs_dropout_prob": 0.1,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "classifier_dropout": null,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dim": 768,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0.1,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu",
+      "hidden_dim": 3072,
+      "hidden_dropout_prob": 0.1,
+      "hidden_size": 768,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 3072,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-12,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 512,
+      "min_length": 0,
+      "model_type": "bert",
+      "n_heads": 12,
+      "n_layers": 6,
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 12,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 12,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_past": true,
+      "output_scores": false,
+      "pad_token_id": 0,
+      "position_embedding_type": "absolute",
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "qa_dropout": 0.1,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "seq_classif_dropout": 0.2,
+      "sinusoidal_pos_embds": false,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_weights_": true,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.49.0",
+      "type_vocab_size": 2,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "vocab_size": 41986
+    }
+  ],
+  "cond_layer_index": 2,
+  "conditioning_layer_index": 2,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 3,
+  "duration_predictor_dropout": 0.1,
+  "duration_predictor_filter_channels": 256,
+  "duration_predictor_flow_bins": 10,
+  "duration_predictor_kernel_size": 3,
+  "duration_predictor_num_flows": 4,
+  "duration_predictor_tail_bound": 5.0,
+  "ffn_dim": 768,
+  "ffn_kernel_size": 3,
+  "flow_size": 192,
+  "hidden_act": "relu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 192,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "leaky_relu_slope": 0.1,
+  "model_type": "bert_vits2",
+  "noise_scale": 0.667,
+  "noise_scale_duration": 0.8,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 6,
+  "num_languages": 3,
+  "num_speakers": 256,
+  "num_tones": 11,
+  "posterior_encoder_num_wavenet_layers": 16,
+  "prior_encoder_num_flows": 4,
+  "prior_encoder_num_flows_layers": 6,
+  "prior_encoder_num_wavenet_layers": 4,
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "sampling_rate": 44100,
+  "speaker_embedding_size": 256,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 1025,
+  "stochastic_duration_prediction_ratio": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "upsample_initial_channel": 512,
+  "upsample_kernel_sizes": [
+    16,
+    16,
+    8,
+    2,
+    2
+  ],
+  "upsample_rates": [
+    8,
+    8,
+    2,
+    2,
+    2
+  ],
+  "use_bias": true,
+  "use_transformer_flow": true,
+  "vocab_size": 112,
+  "wavenet_dilation_rate": 1,
+  "wavenet_dropout": 0.0,
+  "wavenet_kernel_size": 5,
+  "window_size": 4
+}

onnx/model.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d74aa783e97a646c19c60c32e125fb994f3578b78715a71ccc258b566b3dd19a
+size 662923164

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bert_tokenizers": {
+    "zh": "bert_zh"
+  },
+  "processor_class": "BertVits2Processor"
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+  "pad_token": {
+    "content": "_",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "UNK",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "111": {
+      "content": "UNK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "BricksDisplay/ellie-Bert-VITS2--tokenization_bert_vits2.BertVits2Tokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "extra_special_tokens": {},
+  "languages": [
+    "zh"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "_",
+  "processor_class": "BertVits2Processor",
+  "space_token": "SP",
+  "tokenizer_class": "BertVits2Tokenizer",
+  "unk_token": "UNK"
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,114 @@

+{
+  "!": 103,
+  "'": 108,
+  ",": 106,
+  "-": 109,
+  ".": 107,
+  "?": 104,
+  "AA": 1,
+  "E": 2,
+  "EE": 3,
+  "En": 4,
+  "N": 5,
+  "OO": 6,
+  "SP": 110,
+  "UNK": 111,
+  "V": 7,
+  "_": 0,
+  "a": 8,
+  "a:": 9,
+  "aa": 10,
+  "ae": 11,
+  "ah": 12,
+  "ai": 13,
+  "an": 14,
+  "ang": 15,
+  "ao": 16,
+  "aw": 17,
+  "ay": 18,
+  "b": 19,
+  "by": 20,
+  "c": 21,
+  "ch": 22,
+  "d": 23,
+  "dh": 24,
+  "dy": 25,
+  "e": 26,
+  "e:": 27,
+  "eh": 28,
+  "ei": 29,
+  "en": 30,
+  "eng": 31,
+  "er": 32,
+  "ey": 33,
+  "f": 34,
+  "g": 35,
+  "gy": 36,
+  "h": 37,
+  "hh": 38,
+  "hy": 39,
+  "i": 40,
+  "i0": 41,
+  "i:": 42,
+  "ia": 43,
+  "ian": 44,
+  "iang": 45,
+  "iao": 46,
+  "ie": 47,
+  "ih": 48,
+  "in": 49,
+  "ing": 50,
+  "iong": 51,
+  "ir": 52,
+  "iu": 53,
+  "iy": 54,
+  "j": 55,
+  "jh": 56,
+  "k": 57,
+  "ky": 58,
+  "l": 59,
+  "m": 60,
+  "my": 61,
+  "n": 62,
+  "ng": 63,
+  "ny": 64,
+  "o": 65,
+  "o:": 66,
+  "ong": 67,
+  "ou": 68,
+  "ow": 69,
+  "oy": 70,
+  "p": 71,
+  "py": 72,
+  "q": 73,
+  "r": 74,
+  "ry": 75,
+  "s": 76,
+  "sh": 77,
+  "t": 78,
+  "th": 79,
+  "ts": 80,
+  "ty": 81,
+  "u": 82,
+  "u:": 83,
+  "ua": 84,
+  "uai": 85,
+  "uan": 86,
+  "uang": 87,
+  "uh": 88,
+  "ui": 89,
+  "un": 90,
+  "uo": 91,
+  "uw": 92,
+  "v": 93,
+  "van": 94,
+  "ve": 95,
+  "vn": 96,
+  "w": 97,
+  "x": 98,
+  "y": 99,
+  "z": 100,
+  "zh": 101,
+  "zy": 102,
+  "…": 105
+}