add tokenizer

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "g": 6, "h": 7, "i": 8, "k": 9, "l": 10, "m": 11, "n": 12, "o": 13, "p": 14, "q": 15, "r": 16, "s": 17, "t": 18, "u": 19, "v": 20, "x": 21, "y": 22, "à": 23, "á": 24, "ã": 25, "è": 26, "é": 27, "ê": 28, "ì": 29, "í": 30, "ò": 31, "ó": 32, "õ": 33, "ù": 34, "ú": 35, "ý": 36, "ă": 37, "đ": 38, "ĩ": 39, "ũ": 40, "ơ": 41, "ư": 42, "ạ": 43, "ả": 44, "ấ": 45, "ầ": 46, "ẩ": 47, "ẫ": 48, "ậ": 49, "ắ": 50, "ằ": 51, "ẳ": 52, "ẵ": 53, "ặ": 54, "ẹ": 55, "ẻ": 56, "ẽ": 57, "ế": 58, "ề": 59, "ể": 60, "ễ": 61, "ệ": 62, "ỉ": 63, "ị": 64, "ọ": 65, "ỏ": 66, "ố": 67, "ồ": 68, "ổ": 69, "ỗ": 70, "ộ": 71, "ớ": 72, "ờ": 73, "ở": 74, "ỡ": 75, "ợ": 76, "ụ": 77, "ủ": 78, "ứ": 79, "ừ": 80, "ử": 81, "ữ": 82, "ự": 83, "ỳ": 84, "ỷ": 85, "ỹ": 86, "|": 0, "[UNK]": 87, "[PAD]": 89}
+{"(": 1, ")": 2, "*": 3, "0": 4, "1": 5, "2": 6, "3": 7, "4": 8, "5": 9, "7": 10, "8": 11, "9": 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, "à": 40, "á": 41, "ã": 42, "è": 43, "é": 44, "ê": 45, "ì": 46, "í": 47, "ð": 48, "ò": 49, "ó": 50, "õ": 51, "ù": 52, "ú": 53, "ý": 54, "ă": 55, "đ": 56, "ĩ": 57, "ũ": 58, "ơ": 59, "ư": 60, "̀": 61, "́": 62, "̃": 63, "̣": 64, "ạ": 65, "ả": 66, "ấ": 67, "ầ": 68, "ẩ": 69, "ẫ": 70, "ậ": 71, "ắ": 72, "ằ": 73, "ẳ": 74, "ẵ": 75, "ặ": 76, "ẹ": 77, "ẻ": 78, "ẽ": 79, "ế": 80, "ề": 81, "ể": 82, "ễ": 83, "ệ": 84, "ỉ": 85, "ị": 86, "ọ": 87, "ỏ": 88, "ố": 89, "ồ": 90, "ổ": 91, "ỗ": 92, "ộ": 93, "ớ": 94, "ờ": 95, "ở": 96, "ỡ": 97, "ợ": 98, "ụ": 99, "ủ": 100, "ứ": 101, "ừ": 102, "ử": 103, "ữ": 104, "ự": 105, "ỳ": 106, "ỵ": 107, "ỷ": 108, "ỹ": 109, "’": 110, "…": 111, "|": 0, "[UNK]": 112, "[PAD]": 113}