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