correct config and add converted model

config.json

@@ -1,12 +1,16 @@
 {
   "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2Model"
+    "Wav2Vec2ForPreTraining"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
-  "codevector_dim": 384,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
@@ -61,13 +65,16 @@
   "mask_channel_prob": 0.0,
   "mask_channel_selection": "static",
   "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_min_space": 1,
   "mask_time_other": 0.0,
   "mask_time_prob": 0.075,
   "mask_time_selection": "static",
   "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
   "num_attention_heads": 16,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
@@ -76,9 +83,33 @@
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 24,
   "num_negatives": 100,
+  "output_hidden_size": 1024,
   "pad_token_id": 0,
-  "proj_codevector_dim": 256,
+  "proj_codevector_dim": 768,
+  "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": "4.9.2",
-  "vocab_size": 32
+  "transformers_version": "4.18.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15152c284ee5942a27d874ee845afaa88c93d4faed178915fcb62fb002eac61c
+size 1269701863