add head

config.json

@@ -1,8 +1,9 @@
 {
+  "_name_or_path": "./",
   "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
-    "UniSpeechSatForCTC"
+    "UniSpeechSatForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
@@ -46,8 +47,10 @@
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
   "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
   "mask_time_length": 10,
+  "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
   "model_type": "unispeech-sat",
   "num_attention_heads": 2,
@@ -62,8 +65,30 @@
   "pad_token_id": 0,
   "proj_codevector_dim": 256,
   "replace_prob": 0.5,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.12.0.dev0",
+  "transformers_version": "4.16.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32
+  "vocab_size": 32,
+  "xvector_output_dim": 512
 }