Upload tokenizer

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 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,119 @@
+{
+  "%": 111,
+  "&": 93,
+  "'": 31,
+  "*": 107,
+  "+": 30,
+  "/": 54,
+  "0": 47,
+  "1": 62,
+  "2": 49,
+  "3": 5,
+  "4": 22,
+  "5": 35,
+  "6": 85,
+  "7": 29,
+  "8": 88,
+  "9": 65,
+  "<": 112,
+  "=": 110,
+  ">": 7,
+  "[": 8,
+  "[PAD]": 116,
+  "[UNK]": 115,
+  "]": 66,
+  "a": 86,
+  "b": 2,
+  "c": 23,
+  "d": 17,
+  "e": 101,
+  "f": 60,
+  "g": 38,
+  "h": 48,
+  "i": 106,
+  "j": 1,
+  "k": 9,
+  "l": 90,
+  "m": 114,
+  "n": 104,
+  "o": 79,
+  "p": 108,
+  "q": 52,
+  "r": 20,
+  "s": 76,
+  "t": 41,
+  "u": 96,
+  "v": 87,
+  "w": 34,
+  "x": 50,
+  "y": 46,
+  "z": 72,
+  "|": 32,
+  "à": 39,
+  "á": 68,
+  "â": 98,
+  "ã": 59,
+  "è": 81,
+  "é": 83,
+  "ê": 13,
+  "ì": 11,
+  "í": 91,
+  "ò": 57,
+  "ó": 75,
+  "ô": 12,
+  "õ": 73,
+  "ù": 89,
+  "ú": 14,
+  "ý": 6,
+  "ă": 3,
+  "đ": 53,
+  "ĩ": 16,
+  "ũ": 56,
+  "ơ": 33,
+  "ư": 43,
+  "ạ": 51,
+  "ả": 45,
+  "ấ": 80,
+  "ầ": 100,
+  "ẩ": 40,
+  "ẫ": 70,
+  "ậ": 105,
+  "ắ": 21,
+  "ằ": 99,
+  "ẳ": 97,
+  "ẵ": 95,
+  "ặ": 18,
+  "ẹ": 69,
+  "ẻ": 55,
+  "ẽ": 115,
+  "ế": 26,
+  "ề": 84,
+  "ể": 27,
+  "ễ": 77,
+  "ệ": 74,
+  "ỉ": 10,
+  "ị": 103,
+  "ọ": 102,
+  "ỏ": 24,
+  "ố": 109,
+  "ồ": 15,
+  "ổ": 64,
+  "ỗ": 78,
+  "ộ": 42,
+  "ớ": 37,
+  "ờ": 58,
+  "ở": 28,
+  "ỡ": 4,
+  "ợ": 25,
+  "ụ": 113,
+  "ủ": 36,
+  "ứ": 71,
+  "ừ": 94,
+  "ử": 0,
+  "ữ": 82,
+  "ự": 67,
+  "ỳ": 44,
+  "ỷ": 19,
+  "ỹ": 92,
+  "₫": 61
+}