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