add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 40, "</s>": 41}

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 @@
+{"a": 0, "x": 1, "l": 2, "ç": 3, "j": 4, "á": 5, "y": 6, "w": 7, "s": 8, "p": 9, "m": 10, "q": 11, "â": 12, "b": 13, "ã": 14, "ú": 15, "i": 16, "n": 17, "ó": 18, "h": 19, "k": 20, "r": 21, "ê": 23, "e": 24, "ô": 25, "o": 26, "í": 27, "z": 28, "f": 29, "t": 30, "u": 31, "g": 32, "c": 33, "õ": 34, "é": 35, "d": 36, "v": 37, "|": 22, "[UNK]": 38, "[PAD]": 39}