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