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 @@
+{"q": 0, "r": 1, "g": 2, "s": 3, "l": 4, "o": 5, "7": 6, "h": 7, "a": 8, "p": 9, "b": 10, "i": 11, "m": 12, "e": 13, "z": 14, "u": 15, "t": 16, "x": 18, "k": 19, "y": 20, "_": 21, "v": 22, "n": 23, "f": 24, "j": 25, "d": 26, "|": 17, "[UNK]": 27, "[PAD]": 28}