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