Training in progress, step 100

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 130,
+  "<s>": 129,
+  "PAD": 131,
+  "[PAD]": 128
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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_prob": 0.05,
+  "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": 131,
+  "proj_codevector_dim": 768,
+  "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": "4.40.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 132,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6570fc90771bc116352c3afde157748697ec751bcaaa8046c0afaa0158a2ee
+size 1262348680

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
+}

runs/May10_11-50-04_2f71cbd45ded/events.out.tfevents.1715342294.2f71cbd45ded.451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb43cba90ea78bac82ed3feb0c5e0fd52d4c0777f42dc25f785bf6e17c079d6
+size 6175

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "PAD",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "127": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "130": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "131": {
+      "content": "PAD",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "PAD",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "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 sha256:6203d3e1f0e3d153d8b1103a0dec060c7182982b0f3ce6bbaea39c0eaee4ff45
+size 4984

vocab.json

@@ -0,0 +1,131 @@
+{
+  "!": 1,
+  "\"": 2,
+  "&": 3,
+  "'": 4,
+  ",": 5,
+  "-": 6,
+  ".": 7,
+  ":": 8,
+  "?": 9,
+  "A": 10,
+  "B": 11,
+  "C": 12,
+  "D": 13,
+  "E": 14,
+  "F": 15,
+  "G": 16,
+  "I": 17,
+  "J": 18,
+  "K": 19,
+  "L": 20,
+  "M": 21,
+  "N": 22,
+  "O": 23,
+  "P": 24,
+  "R": 25,
+  "S": 26,
+  "T": 27,
+  "V": 28,
+  "W": 29,
+  "X": 30,
+  "Y": 31,
+  "Z": 32,
+  "[PAD]": 128,
+  "[UNK]": 127,
+  "a": 33,
+  "b": 34,
+  "c": 35,
+  "d": 36,
+  "e": 37,
+  "f": 38,
+  "g": 39,
+  "h": 40,
+  "i": 41,
+  "j": 42,
+  "k": 43,
+  "l": 44,
+  "m": 45,
+  "n": 46,
+  "o": 47,
+  "p": 48,
+  "r": 49,
+  "s": 50,
+  "t": 51,
+  "u": 52,
+  "v": 53,
+  "w": 54,
+  "x": 55,
+  "y": 56,
+  "z": 57,
+  "|": 0,
+  "ँ": 59,
+  "ं": 60,
+  "ः": 61,
+  "अ": 62,
+  "आ": 63,
+  "इ": 64,
+  "ई": 65,
+  "उ": 66,
+  "ऊ": 67,
+  "ऋ": 68,
+  "ए": 69,
+  "ऐ": 70,
+  "ऑ": 71,
+  "ओ": 72,
+  "औ": 73,
+  "क": 74,
+  "ख": 75,
+  "ग": 76,
+  "घ": 77,
+  "च": 78,
+  "छ": 79,
+  "ज": 80,
+  "झ": 81,
+  "ञ": 82,
+  "ट": 83,
+  "ठ": 84,
+  "ड": 85,
+  "ढ": 86,
+  "ण": 87,
+  "त": 88,
+  "थ": 89,
+  "द": 90,
+  "ध": 91,
+  "न": 92,
+  "प": 93,
+  "फ": 94,
+  "ब": 95,
+  "भ": 96,
+  "म": 97,
+  "य": 98,
+  "र": 99,
+  "ल": 100,
+  "व": 101,
+  "श": 102,
+  "ष": 103,
+  "स": 104,
+  "ह": 105,
+  "़": 106,
+  "ा": 107,
+  "ि": 108,
+  "ी": 109,
+  "ु": 110,
+  "ू": 111,
+  "ृ": 112,
+  "ॅ": 113,
+  "े": 114,
+  "ै": 115,
+  "ॉ": 116,
+  "ो": 117,
+  "ौ": 118,
+  "्": 119,
+  "ख़": 120,
+  "ज़": 121,
+  "ड़": 122,
+  "ढ़": 123,
+  "।": 124,
+  "–": 125,
+  "‘": 126,
+  "’": 127
+}