Upload model

config.json

@@ -28,7 +28,6 @@
   "architectures": [
     "XcodecModel"
   ],
-  "audio_channels": 1,
   "block_dilations": [
     1,
     1
@@ -52,8 +51,12 @@
   "output_dim": 256,
   "sample_rate": 16000,
   "semantic_model_config": {
+    "_name_or_path": "facebook/hubert-base-ls960",
     "activation_dropout": 0.1,
     "apply_spec_augment": true,
+    "architectures": [
+      "HubertModel"
+    ],
     "attention_dropout": 0.1,
     "classifier_proj_size": 256,
     "conv_bias": false,
@@ -89,12 +92,15 @@
     "ctc_zero_infinity": false,
     "do_stable_layer_norm": false,
     "feat_extract_activation": "gelu",
+    "feat_extract_dropout": 0.0,
     "feat_extract_norm": "group",
-    "feat_proj_dropout": 0.0,
+    "feat_proj_dropout": 0.1,
     "feat_proj_layer_norm": true,
     "final_dropout": 0.1,
+    "gradient_checkpointing": false,
     "hidden_act": "gelu",
     "hidden_dropout": 0.1,
+    "hidden_dropout_prob": 0.1,
     "hidden_size": 768,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
@@ -112,6 +118,7 @@
     "num_conv_pos_embeddings": 128,
     "num_feat_extract_layers": 7,
     "num_hidden_layers": 12,
+    "tokenizer_class": "Wav2Vec2CTCTokenizer",
     "use_weighted_layer_sum": false,
     "vocab_size": 32
   },