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

vocab.json

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