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