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