Upload 8 files

bert_zh/special_tokens_map.json

@@ -1,37 +1,7 @@
-{
-  "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
-  }
-}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

bert_zh/tokenizer_config.json

@@ -1,62 +1,58 @@
-{
-  "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]"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

config.json

@@ -1,6 +1,5 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "../../ellie-BertVITS2-mini",
   "activation_dropout": 0.1,
   "architectures": [
     "BertVits2Model"
@@ -13,41 +12,39 @@
   "bert_configs": [
     {
       "_attn_implementation_autoset": true,
-      "_name_or_path": "distilbert-base-multilingual-cased",
-      "activation": "gelu",
+      "_name_or_path": "albert",
       "add_cross_attention": false,
       "architectures": [
-        "DistilBertForMaskedLM"
+        "AlbertForMaskedLM"
       ],
-      "attention_dropout": 0.1,
-      "attention_probs_dropout_prob": 0.1,
+      "attention_probs_dropout_prob": 0,
       "bad_words_ids": null,
       "begin_suppress_tokens": null,
-      "bos_token_id": null,
+      "bos_token_id": 2,
       "chunk_size_feed_forward": 0,
       "classifier_dropout": null,
+      "classifier_dropout_prob": 0.1,
       "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,
+      "embedding_size": 128,
       "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": null,
+      "eos_token_id": 3,
       "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_act": "relu",
+      "hidden_dropout_prob": 0,
       "hidden_size": 768,
       "id2label": {
         "0": "LABEL_0",
         "1": "LABEL_1"
       },
       "initializer_range": 0.02,
+      "inner_group_num": 1,
       "intermediate_size": 3072,
       "is_decoder": false,
       "is_encoder_decoder": false,
@@ -61,49 +58,43 @@
       "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_groups": 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,
+      "tokenizer_class": "BertTokenizer",
       "top_k": 50,
       "top_p": 1.0,
       "torch_dtype": null,
       "torchscript": false,
-      "transformers_version": "4.49.0",
+      "transformers_version": "4.50.2",
       "type_vocab_size": 2,
       "typical_p": 1.0,
       "use_bfloat16": false,
       "use_cache": true,
-      "vocab_size": 41986
+      "vocab_size": 21128
     }
   ],
   "cond_layer_index": 2,
@@ -166,7 +157,7 @@
   "spectrogram_bins": 1025,
   "stochastic_duration_prediction_ratio": 0.0,
   "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.50.2",
   "upsample_initial_channel": 512,
   "upsample_kernel_sizes": [
     16,

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74aa783e97a646c19c60c32e125fb994f3578b78715a71ccc258b566b3dd19a
-size 662923164
+oid sha256:dad34ada6add382125b12514bc61f0c911e81296b6cfae01ebcb3d0fd8f236b7
+size 599032271

onnx/model_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37066564d2dfe450319a1cc6e6d608321cf44bf3fb634a31d5c5fdf23ba36abc
-size 402022953
+oid sha256:ba8576f0f77ccddf3120efb2297f7f5da60d2a1eceac5bd2596180859849611a
+size 338132060

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43712524472ecd97ce78fb7f455a5561c70fef0f9f767cd0a68fcb7dc1da6e08
-size 277053380
+oid sha256:aaef55d7a487da0d842d0d697bb20503b9f28247e57fb6b8f8d5ddadbbd4ae7c
+size 374317850