Training in progress, epoch 1

.gitignore

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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 109,
+  "<s>": 108
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_dropout_prob": 0.1,
+  "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": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 107,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 110
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 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 sha256:91eab2edc195e73f0675b99369587309389f50854ccfd8dc0079d16d0cc4198b
+size 1262351981

runs/Jul01_14-15-45_6fa7882a54ad/events.out.tfevents.1688221821.6fa7882a54ad.1414.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd695b1f78f4a6a6d958fd055097aed3aac83f2cc23bc8cf40b3d390bf7e23b
+size 5282

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 +1,14 @@
+{
+  "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 sha256:3a564c4a2931aa9c622937d477f26a860957413ceb91277d2ac4ac1afa2d0661
+size 4027

vocab.json

@@ -0,0 +1,110 @@
+{
+  ",": 1,
+  ".": 2,
+  "0": 3,
+  "1": 4,
+  "2": 5,
+  "3": 6,
+  "4": 7,
+  "5": 8,
+  "6": 9,
+  "7": 10,
+  "8": 11,
+  "9": 12,
+  "[PAD]": 107,
+  "[UNK]": 106,
+  "a": 13,
+  "b": 14,
+  "c": 15,
+  "d": 16,
+  "e": 17,
+  "f": 18,
+  "g": 19,
+  "h": 20,
+  "i": 21,
+  "j": 22,
+  "k": 23,
+  "l": 24,
+  "m": 25,
+  "n": 26,
+  "o": 27,
+  "p": 28,
+  "q": 29,
+  "r": 30,
+  "s": 31,
+  "t": 32,
+  "u": 33,
+  "v": 34,
+  "w": 35,
+  "x": 36,
+  "y": 37,
+  "z": 38,
+  "|": 0,
+  "à": 39,
+  "á": 40,
+  "â": 41,
+  "ã": 42,
+  "è": 43,
+  "é": 44,
+  "ê": 45,
+  "ì": 46,
+  "í": 47,
+  "ò": 48,
+  "ó": 49,
+  "ô": 50,
+  "õ": 51,
+  "ù": 52,
+  "ú": 53,
+  "ý": 54,
+  "ă": 55,
+  "đ": 56,
+  "ĩ": 57,
+  "ũ": 58,
+  "ơ": 59,
+  "ư": 60,
+  "ạ": 61,
+  "ả": 62,
+  "ấ": 63,
+  "ầ": 64,
+  "ẩ": 65,
+  "ẫ": 66,
+  "ậ": 67,
+  "ắ": 68,
+  "ằ": 69,
+  "ẳ": 70,
+  "ẵ": 71,
+  "ặ": 72,
+  "ẹ": 73,
+  "ẻ": 74,
+  "ẽ": 75,
+  "ế": 76,
+  "ề": 77,
+  "ể": 78,
+  "ễ": 79,
+  "ệ": 80,
+  "ỉ": 81,
+  "ị": 82,
+  "ọ": 83,
+  "ỏ": 84,
+  "ố": 85,
+  "ồ": 86,
+  "ổ": 87,
+  "ỗ": 88,
+  "ộ": 89,
+  "ớ": 90,
+  "ờ": 91,
+  "ở": 92,
+  "ỡ": 93,
+  "ợ": 94,
+  "ụ": 95,
+  "ủ": 96,
+  "ứ": 97,
+  "ừ": 98,
+  "ử": 99,
+  "ữ": 100,
+  "ự": 101,
+  "ỳ": 102,
+  "ỷ": 103,
+  "ỹ": 104,
+  "₫": 105
+}