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