First version of the your-model-name model and tokenizer.

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "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": 259,
+  "transformers_version": "4.6.0.dev0",
+  "vocab_size": 260
+}

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 sha256:63ce341388d47769a2497a4f39f7008598ffbb18bc28e1230e82e34a56f8f384
+size 1262999831

special_tokens_map.json

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

tokenizer_config.json

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

vocab.json

@@ -0,0 +1 @@
+{"일": 0, "센": 1, "분": 2, "순": 3, "또": 4, "달": 5, "돌": 6, "본": 7, "제": 8, "은": 9, "살": 10, "대": 11, "니": 12, "겨": 13, "근": 14, "오": 15, "채": 16, "도": 17, "능": 18, "다": 19, "쓰": 20, "알": 21, "전": 22, "내": 23, "과": 24, "었": 25, "비": 26, "행": 27, "얘": 28, "의": 29, "경": 30, "업": 31, "형": 32, "개": 33, "1": 34, "갔": 35, "뭔": 36, "영": 37, "칙": 38, "데": 39, "집": 40, "창": 41, "게": 42, "팔": 43, "들": 44, "파": 45, "르": 46, "무": 47, "급": 48, "금": 49, "회": 50, "것": 51, "했": 52, "장": 53, "렇": 54, "법": 55, "시": 56, "닌": 57, "겠": 58, "그": 59, "음": 60, "굉": 61, "테": 62, "있": 63, "말": 64, "온": 65, "왜": 66, "럼": 67, "론": 68, "리": 69, "며": 70, "용": 71, "위": 72, "러": 73, "구": 74, "드": 75, "재": 76, "출": 77, "갚": 78, "낸": 79, "름": 80, "값": 81, "숫": 82, ".": 83, "믄": 84, "에": 85, "같": 86, "많": 87, "료": 88, "당": 89, "새": 90, "떻": 91, "초": 92, "격": 93, "생": 94, "처": 95, "로": 96, "막": 97, "작": 98, "덜": 99, "트": 100, "물": 101, "타": 102, "지": 103, "향": 104, "맞": 105, "자": 106, "각": 107, "사": 108, "려": 109, "를": 110, "가": 111, "발": 112, "면": 113, "역": 114, "어": 115, "간": 116, "네": 117, "특": 118, "바": 119, "크": 120, "길": 121, "하": 122, "든": 123, "냥": 124, "징": 125, "진": 126, "누": 127, "단": 128, "킬": 129, "억": 130, "히": 131, "던": 132, "해": 133, "방": 134, "예": 135, "좀": 136, "람": 137, "융": 138, "국": 139, "할": 140, "린": 141, "록": 142, "컴": 143, "습": 144, "레": 145, "마": 146, "수": 147, "으": 148, "스": 149, "한": 150, "죠": 151, "받": 152, "동": 153, "떤": 154, "없": 155, "속": 156, "져": 157, "요": 158, "까": 159, "뭘": 160, "연": 161, "유": 162, "정": 163, "따": 164, "현": 165, "걸": 166, "좋": 167, "권": 168, "디": 170, "짜": 171, "세": 172, "꿔": 173, "런": 174, "안": 175, "실": 176, "후": 177, "만": 178, "판": 179, "모": 180, "플": 181, "난": 182, "넘": 183, "카": 184, "서": 185, "치": 186, "림": 187, "이": 188, "미": 189, "는": 190, "차": 191, "된": 192, "겁": 193, "운": 194, "졌": 195, "우": 196, "됐": 197, "율": 198, "항": 199, "고": 200, "인": 201, "보": 202, "않": 203, "충": 204, "식": 205, "거": 206, "더": 207, "뭐": 208, "럽": 209, "너": 210, "딧": 211, "기": 212, "여": 213, "험": 214, "상": 215, "삼": 216, "돈": 217, "냐": 218, "느": 219, "주": 220, "액": 221, "페": 222, "건": 223, "나": 224, "중": 225, "른": 226, "웠": 227, "결": 228, "점": 229, "때": 230, "못": 231, "붙": 232, "아": 233, "되": 234, "써": 235, "원": 236, "적": 237, "꾸": 238, "라": 239, "끼": 240, "야": 241, "불": 242, "싶": 243, "번": 244, "약": 245, "래": 246, "입": 247, "빌": 248, "배": 249, "문": 250, "프": 251, "란": 252, "신": 253, "태": 254, "을": 255, "년": 256, "싼": 257, "|": 169, "[UNK]": 258, "[PAD]": 259}