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