add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 61, "</s>": 62}

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, "=": 2, "[": 3, "]": 4, "_": 5, "a": 6, "b": 7, "c": 8, "d": 9, "e": 10, "f": 11, "g": 12, "h": 13, "i": 14, "j": 15, "k": 16, "l": 17, "m": 18, "n": 19, "o": 20, "p": 21, "q": 22, "r": 23, "s": 24, "t": 25, "u": 26, "v": 27, "w": 28, "x": 29, "y": 30, "z": 31, "à": 32, "ã": 33, "ç": 34, "ø": 35, "ā": 36, "ă": 37, "ć": 38, "č": 39, "ī": 40, "œ": 41, "ř": 42, "ū": 43, "ž": 44, "в": 45, "е": 46, "з": 47, "и": 48, "й": 49, "к": 50, "л": 51, "н": 52, "ь": 53, "я": 54, "ụ": 55, "…": 56, "→": 57, "fl": 58, "|": 0, "[UNK]": 59, "[PAD]": 60}