Training in progress, step 100

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "m3hrdadfi/wav2vec2-large-xlsr-persian-v3",
-  "activation_dropout": 0.09216,
+  "_name_or_path": "Harveenchadha/vakyansh-wav2vec2-urdu-urm-60",
+  "activation_dropout": 0.1,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
@@ -9,11 +9,12 @@
     "Wav2Vec2ForCTC"
   ],
   "attention_dropout": 0.1,
-  "bos_token_id": 1,
+  "bos_token": "<s>",
+  "bos_token_id": 0,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -42,49 +43,44 @@
     2
   ],
   "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": true,
+  "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
+  "do_lower_case": false,
+  "do_stable_layer_norm": false,
+  "eos_token": "</s>",
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
+  "feat_extract_norm": "group",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "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,
-  "mask_time_selection": "static",
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
-  "num_attention_heads": 16,
+  "num_attention_heads": 12,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 12,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
-  "pad_token_id": 39,
+  "output_hidden_size": 768,
+  "pad_token": "[PAD]",
+  "pad_token_id": 1,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
@@ -109,7 +105,9 @@
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.15.0",
+  "unk_token": "[UNK]",
   "use_weighted_layer_sum": false,
-  "vocab_size": 40,
+  "vocab_size": 48,
+  "word_delimiter_token": "|",
   "xvector_output_dim": 512
 }

preprocessor_config.json

@@ -3,7 +3,7 @@
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": true,
+  "padding_value": 0,
+  "return_attention_mask": false,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fef673f620dff298070d25711d047f3b362d07dc27ee6b60d308171b749a41
-size 1262087665
+oid sha256:6e4a03ae2a96d85e0cf6aa74c49ec34b27c410179604eb23fe5bf67e11e7cc78
+size 377719255

runs/Jan21_10-57-49_f896580bb99d/1642763254.146815/events.out.tfevents.1642763254.f896580bb99d.76.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcd8b9457f0c3c25e7f5038d01951d7f4febbe5f6873bdd93a4d2cf8656f121
+size 4763

runs/Jan21_10-57-49_f896580bb99d/events.out.tfevents.1642763254.f896580bb99d.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b2966afe42634396ec6a39332672bf9325e7b14b22e64174f3374247f91f1d
+size 5366

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ac0a2fd35c85185506afd015588f4ae7fcbaa0ec864b3c8ace956c2fea5093
+oid sha256:d56f6d44305829a079183cf5f7aae62b708fe14ea753269c46533aaad69cd05b
 size 2927