{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 75, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "Lowercase" }, { "type": "Replace", "pattern": { "Regex": "[^'\u0c93\u0cae\u0c86\u0cad\u0c8b\u0c9a\u0c9f\u0cc1\u0cc7\u0c9c\u0c8f\u0cbe\u0caa\u0cb6\u0ccd\u0c88\u0c94\u0c9e1\u0ca8\u0c8e\u0cb8\u0cb5\u0c87\u0c985\u0c8a\u0cb3\u0c96\u0cc3\u0cc6\\-\u0ca4\u0c9d\u0ca2 \u0c85\u0ca7\u0ccc\u0cb9\u0caf9\u0cab\u0c9b86\u0cb2\u0ca3_\u0ca6\u0cac\u0ca0\u0ca1\u0c833\u0ccb\u0c82\u0c92\u0cc0\u0c95\u0cbf\u0ca5\u0cb0\u0cc2\u0c90\u0cc8\u0c8920\u0c97\u0cca\u0cb747]" }, "content": "" }, { "type": "Strip", "strip_left": true, "strip_right": true }, { "type": "Replace", "pattern": { "Regex": "(?=.)|(?": 75 } } }