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