add tokenizer

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"o": 0, "l": 1, "d": 2, "u": 3, "f": 4, "w": 5, "g": 6, "y": 7, "a": 8, "p": 9, "h": 10, "c": 11, "s": 12, "b": 13, "m": 14, "e": 15, "n": 16, "t": 18, "r": 19, "|": 17, "[UNK]": 20, "[PAD]": 21}
+{"é": 0, "z": 1, "p": 2, "w": 3, "t": 4, "g": 5, "0": 6, "q": 7, "ñ": 8, "n": 9, "m": 10, "a": 11, "f": 12, "d": 13, "s": 14, "h": 15, "6": 16, "i": 18, "u": 19, "8": 20, "v": 21, "l": 22, "y": 23, "b": 24, "7": 25, "2": 26, "o": 27, "e": 28, "'": 29, "4": 30, "5": 31, "r": 32, "9": 33, "j": 34, "k": 35, "c": 36, "1": 37, "x": 38, "3": 39, "|": 17, "[UNK]": 40, "[PAD]": 41}