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