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