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