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 @@
+{"a": 0, "b": 1, "c": 2, "d": 3, "e": 4, "f": 5, "g": 6, "h": 7, "i": 8, "j": 9, "k": 10, "l": 11, "m": 12, "n": 13, "o": 14, "p": 15, "q": 16, "r": 17, "s": 18, "t": 19, "u": 20, "v": 21, "w": 22, "x": 23, "y": 24, "z": 25, "|": 26, "'": 27, "<UNK>": 28, "<PAD>": 29}