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