Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 73,
+  "<s>": 72
+}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "tttarun/trained_model_17_4_1",
+  "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": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "forced_decoder_ids": null,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "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": 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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 71,
+  "proj_codevector_dim": 256,
+  "suppress_tokens": [],
+  "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": "4.29.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 73,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7708ea8a632d44ddf02cfb08f011a4d6c4dd3b5fd36943812bcdfda66419caf5
+size 1262201133

runs/Apr18_07-21-21_s-tttarun-fine--tune--whisper-38e35-76d7b49456-mh75n/1681795286.9426453/events.out.tfevents.1681795286.s-tttarun-fine--tune--whisper-38e35-76d7b49456-mh75n

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fed52ccca220bb4484247a67c4261ad5602934ea6a3bf3cc607e1087e120ed2
+size 5914

runs/Apr18_07-21-21_s-tttarun-fine--tune--whisper-38e35-76d7b49456-mh75n/events.out.tfevents.1681795286.s-tttarun-fine--tune--whisper-38e35-76d7b49456-mh75n

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196b4756ccacae6fd35620b0905daf4c50d1f2d483ea4192e1382fe5fa855e21
+size 5865

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e247d51bfc5aef09eeab13112c151cda4e75ad71516d00d30121f8be2327819
+size 3835

vocab.json

@@ -0,0 +1,74 @@
+{
+  "[PAD]": 71,
+  "[UNK]": 70,
+  "|": 7,
+  "ँ": 47,
+  "ं": 33,
+  "ः": 65,
+  "अ": 23,
+  "आ": 24,
+  "इ": 66,
+  "ई": 11,
+  "उ": 9,
+  "ऊ": 68,
+  "ऋ": 41,
+  "ऍ": 36,
+  "ए": 61,
+  "ऐ": 37,
+  "ऑ": 48,
+  "ओ": 46,
+  "औ": 16,
+  "क": 17,
+  "ख": 12,
+  "ग": 32,
+  "घ": 19,
+  "च": 22,
+  "छ": 50,
+  "ज": 59,
+  "झ": 53,
+  "ञ": 25,
+  "ट": 2,
+  "ठ": 0,
+  "ड": 5,
+  "ढ": 13,
+  "ण": 51,
+  "त": 54,
+  "थ": 67,
+  "द": 64,
+  "ध": 60,
+  "न": 40,
+  "प": 30,
+  "फ": 62,
+  "ब": 1,
+  "भ": 10,
+  "म": 15,
+  "य": 58,
+  "र": 38,
+  "ल": 42,
+  "व": 56,
+  "श": 34,
+  "ष": 6,
+  "स": 55,
+  "ह": 49,
+  "़": 63,
+  "ा": 28,
+  "ि": 29,
+  "ी": 31,
+  "ु": 39,
+  "ू": 52,
+  "ृ": 44,
+  "े": 43,
+  "ै": 45,
+  "ॉ": 27,
+  "ो": 8,
+  "ौ": 21,
+  "्": 69,
+  "क़": 18,
+  "ख़": 14,
+  "ग़": 57,
+  "ज़": 3,
+  "ड़": 26,
+  "ढ़": 35,
+  "फ़": 4,
+  "ॠ": 20
+}