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