Init: 모델 최초 배포

config.json

@@ -0,0 +1,112 @@
+{
+  "_name_or_path": "wav2vec2-conformer-gelu",
+  "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

@@ -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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb65144c5eb50519725c7d71614bf1473be16ee824f36aa0dc2b6c63a014822
+size 719535742

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 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "wav2vec2-conformer-gelu",
+  "pad_token": "<pad>",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

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