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