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