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