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