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