add tokenizer

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<COMMA>", "pad_token": "<PERIOD>"}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<COMMA>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<PERIOD>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"j": 0, "s": 1, "i": 2, "k": 3, "e": 4, "t": 5, "u": 6, "o": 7, "l": 8, "n": 9, "c": 10, "p": 11, "v": 12, "g": 13, "q": 15, "z": 16, "w": 17, "b": 18, "h": 19, "f": 21, "y": 22, "a": 23, "x": 24, "r": 25, "d": 26, "m": 27, "<period>": 28, "<comma>": 29, "|": 20}
+{"p": 0, "i": 1, "r": 2, "x": 3, "s": 4, "g": 5, "v": 6, "c": 7, "a": 8, "j": 9, "f": 10, "b": 11, "w": 12, "n": 13, "l": 15, "o": 16, "z": 18, "q": 19, "e": 20, "t": 21, "k": 22, "y": 23, "m": 24, "h": 25, "d": 26, "u": 27, "[UNK]": 28, "[PAD]": 29, "|": 14}