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