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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "к": 10, "л": 11, "м": 12, "н": 13, "о": 14, "п": 15, "р": 16, "с": 17, "т": 18, "у": 19, "ф": 20, "х": 21, "ц": 22, "ч": 23, "ш": 24, "ђ": 25, "ј": 26, "љ": 27, "њ": 28, "ћ": 29, "џ": 30, "|": 0, "[UNK]": 31, "[PAD]": 32}