{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 39, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "Lowercase" }, { "type": "Replace", "pattern": { "Regex": "[^\u0627\u0646\u0643\u0639\u0625\u063a\u0630\u0629\u0633\u0631\u0637\u062e\u062a\u062c\u0638\u064a\u062f\u2013\u0635\u062b\u0623\u0649\u0636\u062d\u0647 \u0621\u0622\u0628\u0648\u0645\u0644\u0634\u0642\u0632\u0624\u0641_\u0626]" }, "content": "" }, { "type": "Strip", "strip_left": true, "strip_right": true }, { "type": "Replace", "pattern": { "Regex": "(?=.)|(?": 39 } } }