add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 112, "</s>": 113}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"-": 1, "0": 2, "1": 3, "2": 4, "3": 5, "4": 6, "5": 7, "6": 8, "7": 9, "8": 10, "9": 11, "=": 12, "`": 13, "a": 14, "b": 15, "c": 16, "d": 17, "e": 18, "f": 19, "g": 20, "h": 21, "i": 22, "j": 23, "k": 24, "l": 25, "m": 26, "n": 27, "o": 28, "p": 29, "q": 30, "r": 31, "s": 32, "t": 33, "u": 34, "v": 35, "w": 36, "x": 37, "y": 38, "z": 39, "¡": 40, "ß": 41, "à": 42, "á": 43, "â": 44, "ã": 45, "ä": 46, "å": 47, "æ": 48, "ç": 49, "è": 50, "é": 51, "ê": 52, "ë": 53, "í": 54, "ð": 55, "ñ": 56, "ó": 57, "ô": 58, "ö": 59, "ø": 60, "ú": 61, "û": 62, "ü": 63, "þ": 64, "ā": 65, "ă": 66, "ć": 67, "č": 68, "ę": 69, "ě": 70, "ğ": 71, "ī": 72, "ł": 73, "ń": 74, "ō": 75, "ő": 76, "œ": 77, "ř": 78, "š": 79, "ū": 80, "ž": 81, "ʻ": 82, "α": 83, "π": 84, "χ": 85, "в": 86, "е": 87, "з": 88, "и": 89, "й": 90, "к": 91, "л": 92, "н": 93, "ь": 94, "я": 95, "ṃ": 96, "ạ": 97, "ụ": 98, "–": 99, "—": 100, "’": 101, "…": 102, "→": 103, "≡": 104, "京": 105, "大": 106, "都": 107, "阪": 108, "fl": 109, "|": 0, "[UNK]": 110, "[PAD]": 111}