Upload folder using huggingface_hub

config.json

@@ -4,37 +4,26 @@
     "model_type": "acoustic_text_encoder"
   },
   "architectures": [
-    "StyleTextToSpeech2ForConditionalGeneration"
+    "StyleTextToSpeech2Model"
   ],
   "decoder_config": {
     "_attn_implementation_autoset": true,
     "model_type": "decoder"
   },
-  "duration_encoder_config": {
-    "_attn_implementation_autoset": true,
-    "model_type": "duration_encoder"
-  },
-  "duration_predictor_config": {
-    "_attn_implementation_autoset": true,
-    "model_type": "duration_predictor"
-  },
   "initializer_range": 0.02,
   "model_type": "style_text_to_speech_2",
-  "prosodic_text_encoder_config": {
+  "predictor_config": {
     "_attn_implementation_autoset": true,
-    "bert_config": {
+    "model_type": "predictor",
+    "prosodic_text_encoder_sub_model_config": {
       "dropout": 0.1,
       "hidden_size": 768,
       "intermediate_size": 2048,
       "num_attention_heads": 12,
       "vocab_size": 178
-    },
-    "model_type": "prosodic_encoder"
-  },
-  "prosody_predictor_config": {
-    "_attn_implementation_autoset": true,
-    "model_type": "prosody_predictor"
+    }
   },
+  "style_size": 256,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62769f13048fc5753afdf40b09a621ef16ec86c7903851029c7cfe88d6950d05
-size 327127664
+oid sha256:60e4f54b7c744d284326eb7fe1f7c3b5a52e5973c6d8cd3f9e5718089002a524
+size 327129312