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