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