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