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