Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 65,
+  "<s>": 64
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "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
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "./",
+  "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 +1,66 @@
+{
+  "[PAD]": 63,
+  "[UNK]": 62,
+  "|": 0,
+  "가": 1,
+  "갑": 2,
+  "고": 3,
+  "국": 4,
+  "굴": 5,
+  "기": 6,
+  "께": 7,
+  "났": 8,
+  "는": 9,
+  "늘": 10,
+  "니": 11,
+  "다": 12,
+  "더": 13,
+  "동": 14,
+  "든": 15,
+  "랑": 16,
+  "마": 17,
+  "만": 18,
+  "물": 19,
+  "미": 20,
+  "보": 21,
+  "비": 22,
+  "빠": 23,
+  "생": 24,
+  "서": 25,
+  "석": 26,
+  "세": 27,
+  "송": 28,
+  "시": 29,
+  "싶": 30,
+  "싸": 31,
+  "쏟": 32,
+  "아": 33,
+  "어": 34,
+  "얼": 35,
+  "엄": 36,
+  "에": 37,
+  "오": 38,
+  "온": 39,
+  "요": 40,
+  "워": 41,
+  "원": 42,
+  "을": 43,
+  "이": 44,
+  "있": 45,
+  "자": 46,
+  "잔": 47,
+  "제": 48,
+  "졌": 49,
+  "족": 50,
+  "주": 51,
+  "지": 52,
+  "추": 53,
+  "컴": 54,
+  "테": 55,
+  "편": 56,
+  "하": 57,
+  "한": 58,
+  "함": 59,
+  "해": 60,
+  "혼": 61
+}