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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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