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