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