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 @@
+{"p": 0, "y": 2, "s": 3, "b": 4, "e": 5, "o": 6, "g": 7, "l": 8, "m": 9, "f": 10, "d": 11, "a": 12, "k": 13, "r": 14, "i": 15, "t": 16, "w": 17, "n": 18, "h": 19, "u": 20, "c": 21, "|": 1, "[UNK]": 22, "[PAD]": 23}