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