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