add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 64, "</s>": 65}

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

vocab.json

@@ -0,0 +1 @@
+{"/": 1, "\\": 2, "`": 3, "a": 4, "b": 5, "c": 6, "d": 7, "e": 8, "f": 9, "g": 10, "h": 11, "i": 12, "j": 13, "k": 14, "l": 15, "m": 16, "n": 17, "o": 18, "p": 19, "q": 20, "r": 21, "s": 22, "t": 23, "u": 24, "v": 25, "w": 26, "x": 27, "y": 28, "z": 29, "}": 30, "«": 31, "°": 32, "´": 33, "¼": 34, "á": 35, "é": 36, "ï": 37, "ñ": 38, "ö": 39, "ü": 40, "ā": 41, "ć": 42, "ğ": 43, "ī": 44, "ō": 45, "ˮ": 46, "́": 47, "а": 48, "в": 49, "е": 50, "с": 51, "і": 52, "–": 53, "—": 54, "’": 55, "‟": 56, "…": 57, "″": 58, "‽": 59, "€": 60, "™": 61, "|": 0, "[UNK]": 62, "[PAD]": 63}