add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"\"": 1, "%": 2, "'": 3, ",": 4, ".": 5, "?": 6, "A": 7, "B": 8, "C": 9, "D": 10, "E": 11, "F": 12, "G": 13, "H": 14, "I": 15, "K": 16, "L": 17, "M": 18, "N": 19, "O": 20, "P": 21, "Q": 22, "R": 23, "S": 24, "T": 25, "V": 26, "Y": 27, "Z": 28, "a": 29, "b": 30, "c": 31, "d": 32, "e": 33, "f": 34, "g": 35, "h": 36, "i": 37, "j": 38, "k": 39, "l": 40, "m": 41, "n": 42, "o": 43, "p": 44, "r": 45, "s": 46, "t": 47, "u": 48, "v": 49, "y": 50, "z": 51, "Ç": 52, "Ö": 53, "Ü": 54, "â": 55, "ç": 56, "ö": 57, "ü": 58, "ğ": 59, "İ": 60, "ı": 61, "Ş": 62, "ş": 63, "�": 64, "|": 0, "[UNK]": 65, "[PAD]": 66}