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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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