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