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