Initial commit

Browse files

Files changed (6) hide show

config.json +112 -0
preprocessor_config.json +9 -0
pytorch_model.bin +3 -0
special_tokens_map.json +6 -0
tokenizer_config.json +12 -0
vocab.json +113 -0

config.json ADDED Viewed

	@@ -0,0 +1,112 @@

+{
+  "_name_or_path": "42MARU/ko-spelling-wav2vec2-conformer-del-1s",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ConformerForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_depthwise_kernel_size": 31,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "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": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.05,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-conformer",
+  "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": 0,
+  "position_embeddings_type": "relative",
+  "proj_codevector_dim": 256,
+  "rotary_embedding_base": 10000,
+  "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": "4.20.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 111,
+  "xvector_output_dim": 512
+}

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bebc95edffc363e8c90fb100eee9853a25150ec463a1012c2f388cd78bd49a15
+size 719532158

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "42MARU/ko-spelling-wav2vec2-conformer-del-1s",
+  "pad_token": "<pad>",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,113 @@

+{
+  "%": 86,
+  "'": 107,
+  "0": 51,
+  "1": 52,
+  "2": 58,
+  "3": 62,
+  "4": 65,
+  "5": 63,
+  "6": 67,
+  "7": 81,
+  "8": 77,
+  "9": 74,
+  "</s>": 3,
+  "<pad>": 0,
+  "<s>": 2,
+  "<unk>": 1,
+  "A": 68,
+  "B": 87,
+  "C": 78,
+  "D": 83,
+  "E": 64,
+  "F": 91,
+  "G": 89,
+  "H": 94,
+  "I": 69,
+  "J": 102,
+  "K": 95,
+  "L": 84,
+  "M": 80,
+  "N": 72,
+  "O": 70,
+  "P": 82,
+  "Q": 101,
+  "R": 76,
+  "S": 71,
+  "T": 66,
+  "U": 90,
+  "V": 93,
+  "W": 98,
+  "X": 100,
+  "Y": 99,
+  "Z": 103,
+  "|": 4,
+  "°": 110,
+  "ᄀ": 8,
+  "ᄁ": 36,
+  "ᄂ": 17,
+  "ᄃ": 14,
+  "ᄄ": 34,
+  "ᄅ": 18,
+  "ᄆ": 23,
+  "ᄇ": 27,
+  "ᄈ": 61,
+  "ᄉ": 15,
+  "ᄊ": 49,
+  "ᄋ": 5,
+  "ᄌ": 13,
+  "ᄍ": 53,
+  "ᄎ": 32,
+  "ᄏ": 47,
+  "ᄐ": 39,
+  "ᄑ": 43,
+  "ᄒ": 19,
+  "ᅡ": 6,
+  "ᅢ": 24,
+  "ᅣ": 42,
+  "ᅤ": 60,
+  "ᅥ": 11,
+  "ᅦ": 20,
+  "ᅧ": 25,
+  "ᅨ": 44,
+  "ᅩ": 12,
+  "ᅪ": 33,
+  "ᅫ": 54,
+  "ᅬ": 35,
+  "ᅭ": 29,
+  "ᅮ": 21,
+  "ᅯ": 41,
+  "ᅰ": 96,
+  "ᅱ": 50,
+  "ᅲ": 46,
+  "ᅳ": 9,
+  "ᅴ": 38,
+  "ᅵ": 7,
+  "ᆨ": 26,
+  "ᆩ": 75,
+  "ᆪ": 104,
+  "ᆫ": 10,
+  "ᆬ": 97,
+  "ᆭ": 45,
+  "ᆮ": 59,
+  "ᆯ": 16,
+  "ᆰ": 79,
+  "ᆱ": 85,
+  "ᆲ": 92,
+  "ᆳ": 109,
+  "ᆴ": 106,
+  "ᆵ": 108,
+  "ᆶ": 88,
+  "ᆷ": 28,
+  "ᆸ": 31,
+  "ᆹ": 55,
+  "ᆺ": 37,
+  "ᆻ": 30,
+  "ᆼ": 22,
+  "ᆽ": 56,
+  "ᆾ": 73,
+  "ᆿ": 105,
+  "ᇀ": 48,
+  "ᇁ": 57,
+  "ᇂ": 40
+}