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