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