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