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