add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 50, "</s>": 51}
+{"<s>": 51, "</s>": 52}

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

vocab.json

@@ -1 +1 @@
-{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "³": 27, "á": 28, "ä": 29, "é": 30, "í": 31, "ó": 32, "ô": 33, "ö": 34, "ú": 35, "ý": 36, "č": 37, "ď": 38, "ĺ": 39, "ľ": 40, "ň": 41, "ŕ": 42, "š": 43, "ť": 44, "ž": 45, "̌": 46, "„": 47, "|": 0, "[UNK]": 48, "[PAD]": 49}
+{"`": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "³": 28, "á": 29, "ä": 30, "é": 31, "í": 32, "ó": 33, "ô": 34, "ö": 35, "ú": 36, "ý": 37, "č": 38, "ď": 39, "ĺ": 40, "ľ": 41, "ň": 42, "ŕ": 43, "š": 44, "ť": 45, "ž": 46, "̌": 47, "„": 48, "|": 0, "[UNK]": 49, "[PAD]": 50}