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