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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"y": 0, "u": 1, "q": 3, "r": 4, "i": 5, "f": 6, "o": 7, "a": 8, "k": 9, "l": 10, "b": 11, "t": 12, "w": 13, "z": 14, "x": 15, "g": 16, "m": 17, "h": 18, "'": 19, "d": 20, "c": 21, "v": 22, "j": 23, "s": 24, "â": 25, "p": 26, "e": 27, "n": 28, "|": 2, "[UNK]": 29, "[PAD]": 30}