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