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 +1,96 @@
+{
+  "4": 25,
+  ":": 84,
+  "A": 81,
+  "B": 20,
+  "C": 39,
+  "D": 59,
+  "E": 11,
+  "G": 75,
+  "H": 53,
+  "I": 24,
+  "K": 56,
+  "L": 60,
+  "M": 90,
+  "N": 21,
+  "O": 40,
+  "P": 19,
+  "Q": 15,
+  "R": 35,
+  "S": 80,
+  "T": 34,
+  "U": 70,
+  "V": 83,
+  "X": 88,
+  "Y": 30,
+  "[PAD]": 93,
+  "[UNK]": 92,
+  "|": 16,
+  "À": 91,
+  "Á": 69,
+  "Â": 78,
+  "Ã": 62,
+  "È": 0,
+  "É": 47,
+  "Ê": 41,
+  "Ì": 44,
+  "Í": 5,
+  "Ò": 86,
+  "Ó": 77,
+  "Ô": 29,
+  "Õ": 23,
+  "Ù": 6,
+  "Ú": 73,
+  "Ý": 38,
+  "Ă": 89,
+  "Đ": 10,
+  "Ĩ": 8,
+  "Ũ": 45,
+  "Ơ": 46,
+  "Ư": 7,
+  "Ạ": 12,
+  "Ả": 22,
+  "Ấ": 26,
+  "Ầ": 17,
+  "Ẩ": 67,
+  "Ẫ": 64,
+  "Ậ": 51,
+  "Ắ": 54,
+  "Ằ": 4,
+  "Ẳ": 1,
+  "Ẵ": 18,
+  "Ặ": 50,
+  "Ẹ": 68,
+  "Ẻ": 58,
+  "Ẽ": 76,
+  "Ế": 85,
+  "Ề": 79,
+  "Ể": 32,
+  "Ễ": 71,
+  "Ệ": 27,
+  "Ỉ": 52,
+  "Ị": 36,
+  "Ọ": 74,
+  "Ỏ": 65,
+  "Ố": 49,
+  "Ồ": 3,
+  "Ổ": 82,
+  "Ỗ": 33,
+  "Ộ": 14,
+  "Ớ": 48,
+  "Ờ": 72,
+  "Ở": 43,
+  "Ỡ": 55,
+  "Ợ": 87,
+  "Ụ": 31,
+  "Ủ": 42,
+  "Ứ": 13,
+  "Ừ": 2,
+  "Ử": 61,
+  "Ữ": 57,
+  "Ự": 9,
+  "Ỳ": 37,
+  "Ỵ": 66,
+  "Ỷ": 28,
+  "Ỹ": 63
+}