Training in progress, step 100

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
-  "activation_dropout": 0.0,
+  "_name_or_path": "Harveenchadha/vakyansh-wav2vec2-hindi-him-4200",
+  "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": 768,
+  "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -44,49 +45,43 @@
   "ctc_loss_reduction": "mean",
   "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": 62,
-  "proj_codevector_dim": 768,
+  "output_hidden_size": 768,
+  "pad_token": "[PAD]",
+  "pad_token_id": 1,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,
@@ -110,7 +105,9 @@
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.15.0",
+  "unk_token": "[UNK]",
   "use_weighted_layer_sum": false,
-  "vocab_size": 65,
+  "vocab_size": 67,
+  "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 sha256:2a9f83e1a6280b2c0363c823d4f910b1f56855d43faf79cc26c26f0dc77a6f35
-size 1262190193
+oid sha256:eb7d4ed21a27b8c98145950b9612c2a31eaaa7e8833164e95e5defaf231527dc
+size 377777687

runs/Jan21_22-25-09_e132e839b4f5/1642803942.7165868/events.out.tfevents.1642803942.e132e839b4f5.1628.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc716ebfdcd1cef46d2e2484fcd09803f067b5453d49e59ae43e27d8da17409
+size 4772

runs/Jan21_22-25-09_e132e839b4f5/events.out.tfevents.1642803942.e132e839b4f5.1628.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e086b83b73f9d0506eb0ca4966070bb0c68089548214648925a44769cc64773
+size 5378

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208abc3de73942bd26d86e2fa277ba70414695797d1668b474992d4a2090ef2a
+oid sha256:adafbeab2d272de10593f84282e2f1e58fa5e7c31435d41da28151626f82d597
 size 2927