add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 41, "</s>": 42}

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 @@
+{"p": 0, "á": 1, "n": 2, "h": 3, "é": 4, "ê": 5, "õ": 6, "q": 7, "e": 8, "g": 9, "s": 10, "y": 11, "a": 12, "r": 13, "b": 14, "ú": 15, "w": 16, "í": 17, "ó": 18, "i": 19, "m": 20, "z": 21, "u": 22, "v": 23, "ô": 24, "o": 25, "x": 26, "l": 27, "d": 28, "t": 29, "à": 30, "â": 32, "j": 33, "k": 34, "ç": 35, "c": 36, "f": 37, "ã": 38, "|": 31, "[UNK]": 39, "[PAD]": 40}