Update config.json

config.json

@@ -1,7 +1,7 @@
 {
   "activation_dropout": 0.1,
   "architectures": [
-    "VitsModel"
+    "VitsModelForPreTraining"
   ],
   "attention_dropout": 0.1,
   "depth_separable_channels": 2,
@@ -41,7 +41,6 @@
   "hidden_act": "relu",
   "hidden_dropout": 0.1,
   "hidden_size": 192,
-  "hop_length": 256,
   "initializer_range": 0.02,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
@@ -78,12 +77,11 @@
     11
   ],
   "sampling_rate": 16000,
-  "segment_size": 8192,
   "speaker_embedding_size": 0,
   "speaking_rate": 1.0,
   "spectrogram_bins": 513,
   "torch_dtype": "float32",
-  "transformers_version": "4.36.0",
+  "transformers_version": "4.33.0.dev0",
   "upsample_initial_channel": 512,
   "upsample_kernel_sizes": [
     16,
@@ -99,9 +97,10 @@
   ],
   "use_bias": true,
   "use_stochastic_duration_prediction": true,
-  "vocab_size": 25,
+  "vocab_size": 64,
   "wavenet_dilation_rate": 1,
   "wavenet_dropout": 0.0,
   "wavenet_kernel_size": 5,
   "window_size": 4
 }
+