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 @@
+{"j": 0, "l": 1, "e": 2, "n": 3, "t": 4, "g": 5, "i": 6, "r": 7, "a": 8, "u": 9, "'": 10, "k": 11, "q": 12, "s": 13, "c": 14, "1": 15, "h": 16, "v": 17, "p": 18, "f": 19, "m": 20, "z": 21, "x": 22, "o": 23, "w": 25, "b": 26, "2": 27, "d": 28, "y": 29, "[UNK]": 30, "[PAD]": 31, "|": 24}