add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 42, "</s>": 43}

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 @@
+{"o": 0, "ñ": 1, "ã": 2, "w": 3, "s": 4, "ç": 5, "h": 6, "â": 7, "z": 8, "f": 9, "j": 10, "ô": 11, "ú": 12, "é": 13, "k": 14, "g": 15, "e": 16, "p": 18, "d": 19, "t": 20, "x": 21, "í": 22, "c": 23, "y": 24, "ê": 25, "õ": 26, "á": 27, "v": 28, "q": 29, "n": 30, "u": 31, "b": 32, "à": 33, "m": 34, "l": 35, "ó": 36, "a": 37, "i": 38, "r": 39, "|": 17, "[UNK]": 40, "[PAD]": 41}