Training in progress, step 200

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 1024,
@@ -50,16 +50,16 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.05,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_size": 1280,
   "initializer_range": 0.02,
   "intermediate_size": 5120,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -77,7 +77,7 @@
   "num_hidden_layers": 48,
   "num_negatives": 100,
   "output_hidden_size": 1280,
-  "pad_token_id": 0,
+  "pad_token_id": 27,
   "proj_codevector_dim": 1024,
   "tdnn_dilation": [
     1,
@@ -103,6 +103,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.33.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 154,
+  "vocab_size": 30,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf32b45ca36cc5799f94429f1211a53c222390dadf5d98511caa383f18769bbc
-size 3859764813
+oid sha256:77f5e112f317dd3355582534c6da788ee9154e6d96c7b8934868d7d5c0eb982d
+size 3859129421

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd9127a753f0eed1ba4ab3acc9515f3bc826bd2b3de3c750f440aefe3886193
+oid sha256:5e7284ed5528798c661532f7b1adcda93faa064ad0df50a5513dc24f0640ac6d
 size 4027