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