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": " ", "return_attention_mask": true, "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"k": 0, "c": 1, "p": 2, " ": 3, "s": 4, "t": 5, "e": 6, "i": 7, "o": 8, "m": 9, "l": 10, "d": 11, "n": 12, "a": 13, "b": 14, "h": 15, "r": 16, "f": 17, "|": 3, "UNK": 19, "[PAD]": 20}