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