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