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