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