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