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