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