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