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 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,99 @@
+{
+  "'": 9,
+  "[PAD]": 96,
+  "[UNK]": 95,
+  "a": 24,
+  "b": 3,
+  "c": 15,
+  "d": 49,
+  "e": 0,
+  "f": 19,
+  "g": 41,
+  "h": 84,
+  "i": 40,
+  "j": 94,
+  "k": 1,
+  "l": 26,
+  "m": 47,
+  "n": 18,
+  "o": 83,
+  "p": 61,
+  "q": 92,
+  "r": 31,
+  "s": 51,
+  "t": 2,
+  "u": 81,
+  "v": 35,
+  "w": 85,
+  "x": 70,
+  "y": 65,
+  "z": 54,
+  "|": 4,
+  "à": 6,
+  "á": 91,
+  "â": 16,
+  "ã": 32,
+  "è": 48,
+  "é": 57,
+  "ê": 17,
+  "ì": 68,
+  "í": 75,
+  "ò": 78,
+  "ó": 14,
+  "ô": 39,
+  "õ": 93,
+  "ù": 10,
+  "ú": 8,
+  "ý": 27,
+  "ă": 82,
+  "đ": 55,
+  "ĩ": 56,
+  "ũ": 63,
+  "ơ": 73,
+  "ư": 66,
+  "ạ": 38,
+  "ả": 77,
+  "ấ": 50,
+  "ầ": 67,
+  "ẩ": 52,
+  "ẫ": 79,
+  "ậ": 72,
+  "ắ": 22,
+  "ằ": 90,
+  "ẳ": 74,
+  "ẵ": 87,
+  "ặ": 53,
+  "ẹ": 29,
+  "ẻ": 30,
+  "ẽ": 59,
+  "ế": 20,
+  "ề": 21,
+  "ể": 43,
+  "ễ": 71,
+  "ệ": 25,
+  "ỉ": 23,
+  "ị": 80,
+  "ọ": 44,
+  "ỏ": 28,
+  "ố": 12,
+  "ồ": 76,
+  "ổ": 42,
+  "ỗ": 58,
+  "ộ": 34,
+  "ớ": 13,
+  "ờ": 36,
+  "ở": 89,
+  "ỡ": 45,
+  "ợ": 7,
+  "ụ": 37,
+  "ủ": 62,
+  "ứ": 60,
+  "ừ": 86,
+  "ử": 64,
+  "ữ": 5,
+  "ự": 88,
+  "ỳ": 11,
+  "ỵ": 69,
+  "ỷ": 33,
+  "ỹ": 46
+}