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 @@
+{"у": 0, "ц": 1, "э": 2, "х": 3, "в": 4, "б": 5, "й": 6, "ч": 7, "ь": 8, "а": 9, "м": 10, "н": 11, "е": 12, "ф": 13, "г": 14, "л": 15, "ъ": 16, "и": 17, "о": 18, "к": 19, "щ": 20, "ё": 21, "р": 22, "д": 23, "я": 24, "ы": 26, "ж": 27, "з": 28, "т": 29, "ш": 30, "с": 31, "п": 32, "ю": 33, "|": 25, "[UNK]": 34, "[PAD]": 35}