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