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