Training in progress, step 500

config.json

@@ -1,12 +1,16 @@
 {
   "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
+  "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": false,
@@ -48,7 +52,6 @@
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "freeze_feat_extract_train": true,
-  "gradient_checkpointing": true,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
   "hidden_size": 768,
@@ -62,8 +65,10 @@
   "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": 0.05,
@@ -71,6 +76,7 @@
   "model_type": "wav2vec2",
   "no_mask_channel_overlap": false,
   "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
   "num_attention_heads": 12,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
@@ -79,9 +85,33 @@
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 12,
   "num_negatives": 100,
+  "output_hidden_size": 768,
   "pad_token_id": 29,
   "proj_codevector_dim": 256,
+  "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": "4.9.1",
-  "vocab_size": 32
+  "transformers_version": "4.15.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2fcf8a34b2fa94c6d539d796740544265edc82f62dc78e9709554e9b49afaf
+oid sha256:c23b06f74030974c95aefc3171a0f413843effaf059ad482bba951996a320f28
 size 377670039

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3525ce693ff1a560cef03e05cced987bc53418307793029bef8d9b71b29cf858
-size 2607
+oid sha256:d8ec2b8d3bd6abd93e591dc453ae394ea802bd4373ed86cf84f21f9ed38d98ce
+size 2927