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