Training in progress, step 100

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "Harveenchadha/vakyansh-wav2vec2-urdu-urm-60",
-  "activation_dropout": 0.1,
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
@@ -9,12 +9,11 @@
     "Wav2Vec2ForCTC"
   ],
   "attention_dropout": 0.1,
-  "bos_token": "<s>",
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
+  "codevector_dim": 768,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -45,43 +44,49 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_lower_case": false,
-  "do_stable_layer_norm": false,
-  "eos_token": "</s>",
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.1,
+  "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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": 12,
+  "num_attention_heads": 16,
   "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": 12,
+  "num_hidden_layers": 24,
   "num_negatives": 100,
-  "output_hidden_size": 768,
-  "pad_token": "[PAD]",
+  "output_hidden_size": 1024,
   "pad_token_id": 1,
-  "proj_codevector_dim": 256,
+  "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
     2,
@@ -105,9 +110,7 @@
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.15.0",
-  "unk_token": "[UNK]",
   "use_weighted_layer_sum": false,
   "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,
-  "return_attention_mask": false,
+  "padding_value": 0.0,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83bfc42e2f8dcf26d6fd1d351443cff72b814155f4312d3241922f3e6c6b736
-size 377719255
+oid sha256:441d1fb6de0dc20ac733c684ee969ce7edb083ab2ae03d0018d03a65bfd7b79b
+size 1262120497

runs/Jan21_14-26-50_c363f86c0f43/1642775237.6651278/events.out.tfevents.1642775237.c363f86c0f43.73.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e736b0d4eb9bf93d50034ac17328ffffcf704187c7dde848c18bebe2e8aa4d98
+size 4763

runs/Jan21_14-26-50_c363f86c0f43/events.out.tfevents.1642775237.c363f86c0f43.73.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9155f228263e08847793773e1470a6917fbf1597a2426dcbcaa77fef396f324
+size 5459

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d56f6d44305829a079183cf5f7aae62b708fe14ea753269c46533aaad69cd05b
+oid sha256:149328fe768903b1005e2c0d7eb81ee590c8499ecef8e922e9295e3c641fadb6
 size 2927