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