Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 124,
+  "<s>": 123
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
+  "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": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 123,
+  "proj_codevector_dim": 256,
+  "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": "4.31.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 125,
+  "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": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c855d2f6d9b0114e6487801bc939a611d2de9ade5fc4ee5ade401054203b50
+size 377944801

runs/Jun18_09-50-27_e381e886a6f2/events.out.tfevents.1687082488.e381e886a6f2.1446.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c911700a1df305926e457a696bc8d36cd12acfd1b499af0567c2ee1e0dd598
+size 5585

runs/Jun18_10-11-46_e381e886a6f2/events.out.tfevents.1687083114.e381e886a6f2.7070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e5fc41729e9ab27f7276d7aedaf1a55f823cf86501ca65cdd4e650a2de6a55
+size 5585

runs/Jun18_10-17-33_e381e886a6f2/events.out.tfevents.1687084274.e381e886a6f2.13957.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc90eb5ee3046e98a0a1015b1cf9a00de30129debedce1fe3175f0a5c647bb0
+size 7008

special_tokens_map.json

@@ -0,0 +1,50 @@
+{
+  "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
+    },
+    {
+      "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 +1,14 @@
+{
+  "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 sha256:99ac6afff66fdd6dfc07562cff9d0e8e7fe04fd381a2d721909e79e908058718
+size 4027

vocab.json

@@ -0,0 +1,126 @@
+{
+  "!": 1,
+  "\"": 2,
+  "%": 3,
+  "&": 4,
+  "'": 5,
+  "*": 6,
+  "+": 7,
+  ",": 8,
+  "-": 9,
+  ".": 10,
+  "/": 11,
+  "0": 12,
+  "1": 13,
+  "2": 14,
+  "3": 15,
+  "4": 16,
+  "5": 17,
+  "6": 18,
+  "7": 19,
+  "8": 20,
+  "9": 21,
+  ":": 22,
+  "<": 23,
+  "=": 24,
+  ">": 25,
+  "?": 26,
+  "[": 27,
+  "[PAD]": 123,
+  "[UNK]": 122,
+  "]": 28,
+  "a": 29,
+  "b": 30,
+  "c": 31,
+  "d": 32,
+  "e": 33,
+  "f": 34,
+  "g": 35,
+  "h": 36,
+  "i": 37,
+  "j": 38,
+  "k": 39,
+  "l": 40,
+  "m": 41,
+  "n": 42,
+  "o": 43,
+  "p": 44,
+  "q": 45,
+  "r": 46,
+  "s": 47,
+  "t": 48,
+  "u": 49,
+  "v": 50,
+  "w": 51,
+  "x": 52,
+  "y": 53,
+  "z": 54,
+  "|": 0,
+  "à": 56,
+  "á": 57,
+  "â": 58,
+  "ã": 59,
+  "è": 60,
+  "é": 61,
+  "ê": 62,
+  "ì": 63,
+  "í": 64,
+  "ò": 65,
+  "ó": 66,
+  "ô": 67,
+  "õ": 68,
+  "ù": 69,
+  "ú": 70,
+  "ý": 71,
+  "ă": 72,
+  "đ": 73,
+  "ĩ": 74,
+  "ũ": 75,
+  "ơ": 76,
+  "ư": 77,
+  "ạ": 78,
+  "ả": 79,
+  "ấ": 80,
+  "ầ": 81,
+  "ẩ": 82,
+  "ẫ": 83,
+  "ậ": 84,
+  "ắ": 85,
+  "ằ": 86,
+  "ẳ": 87,
+  "ẵ": 88,
+  "ặ": 89,
+  "ẹ": 90,
+  "ẻ": 91,
+  "ẽ": 92,
+  "ế": 93,
+  "ề": 94,
+  "ể": 95,
+  "ễ": 96,
+  "ệ": 97,
+  "ỉ": 98,
+  "ị": 99,
+  "ọ": 100,
+  "ỏ": 101,
+  "ố": 102,
+  "ồ": 103,
+  "ổ": 104,
+  "ỗ": 105,
+  "ộ": 106,
+  "ớ": 107,
+  "ờ": 108,
+  "ở": 109,
+  "ỡ": 110,
+  "ợ": 111,
+  "ụ": 112,
+  "ủ": 113,
+  "ứ": 114,
+  "ừ": 115,
+  "ử": 116,
+  "ữ": 117,
+  "ự": 118,
+  "ỳ": 119,
+  "ỷ": 120,
+  "ỹ": 121,
+  "₫": 122
+}