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