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