add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 44, "</s>": 45}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"c": 1, "а": 2, "б": 3, "в": 4, "г": 5, "д": 6, "е": 7, "ж": 8, "з": 9, "и": 10, "к": 11, "л": 12, "м": 13, "н": 14, "о": 15, "п": 16, "р": 17, "с": 18, "т": 19, "у": 20, "ф": 21, "х": 22, "ц": 23, "ч": 24, "ш": 25, "ы": 26, "ь": 27, "џ": 28, "қ": 29, "ҟ": 30, "ҩ": 31, "ҭ": 32, "ҳ": 33, "ҵ": 34, "ҷ": 35, "ҽ": 36, "ҿ": 37, "ә": 38, "ӡ": 39, "ӷ": 40, "ԥ": 41, "|": 0, "[UNK]": 42, "[PAD]": 43}