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 @@
+{"i": 0, "s": 2, "r": 3, "h": 4, "n": 5, "k": 6, "c": 7, "t": 8, "p": 9, "d": 10, "e": 11, "m": 12, "o": 13, "a": 14, "l": 15, "f": 16, "b": 17, "|": 1, "[UNK]": 18, "[PAD]": 19}