{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Jawi-to-Rumi"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\">\n",
    "\n",
    "This tutorial is available as an IPython notebook at [Malaya/example/jawi-rumi](https://github.com/huseinzol05/Malaya/tree/master/example/jawi-rumi).\n",
    "    \n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-warning\">\n",
    "\n",
    "This module heavily trained on news and wikipedia dataset.\n",
    "    \n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Explanation\n",
    "\n",
    "Originally from https://www.ejawi.net/converterV2.php?go=rumi able to convert Rumi to Jawi using heuristic method. So Malaya convert from heuristic and map it using deep learning model by inverse the dataset.\n",
    "\n",
    "`چوميل` -> `comel`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import logging\n",
    "\n",
    "logging.basicConfig(level=logging.INFO)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:numexpr.utils:NumExpr defaulting to 8 threads.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 5.71 s, sys: 1.06 s, total: 6.77 s\n",
      "Wall time: 7.65 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "import malaya"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### List available Transformer model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:malaya.jawi_rumi:tested on first 10k Jawi-Rumi test set, dataset at https://huggingface.co/datasets/mesolitica/rumi-jawi\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Size (MB)</th>\n",
       "      <th>Quantized Size (MB)</th>\n",
       "      <th>CER</th>\n",
       "      <th>WER</th>\n",
       "      <th>Suggested length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>small</th>\n",
       "      <td>42.7</td>\n",
       "      <td>13.1</td>\n",
       "      <td>0.004477</td>\n",
       "      <td>0.013642</td>\n",
       "      <td>256.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>base</th>\n",
       "      <td>234.0</td>\n",
       "      <td>63.8</td>\n",
       "      <td>0.000764</td>\n",
       "      <td>0.003042</td>\n",
       "      <td>256.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Size (MB)  Quantized Size (MB)       CER       WER  Suggested length\n",
       "small       42.7                 13.1  0.004477  0.013642             256.0\n",
       "base       234.0                 63.8  0.000764  0.003042             256.0"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "malaya.jawi_rumi.available_transformer()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load Transformer model\n",
    "\n",
    "```python\n",
    "def transformer(model='base', quantized: bool = False, **kwargs):\n",
    "    \"\"\"\n",
    "    Load transformer encoder-decoder model to convert jawi to rumi.\n",
    "\n",
    "    Parameters\n",
    "    ----------\n",
    "    model : str, optional (default='base')\n",
    "        Model architecture supported. Allowed values:\n",
    "\n",
    "        * ``'small'`` - Transformer SMALL parameters.\n",
    "        * ``'base'`` - Transformer BASE parameters.\n",
    "\n",
    "    quantized : bool, optional (default=False)\n",
    "        if True, will load 8-bit quantized model.\n",
    "        Quantized model not necessary faster, totally depends on the machine.\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    result: malaya.model.tf.JawiRumi class\n",
    "    \"\"\"\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = malaya.jawi_rumi.transformer()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load Quantized model\n",
    "\n",
    "To load 8-bit quantized model, simply pass `quantized = True`, default is `False`.\n",
    "\n",
    "We can expect slightly accuracy drop from quantized model, and not necessary faster than normal 32-bit float model, totally depends on machine."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "quantized_model = malaya.jawi_rumi.transformer(quantized = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Predict using greedy decoder\n",
    "\n",
    "```python\n",
    "def greedy_decoder(self, strings: List[str]):\n",
    "    \"\"\"\n",
    "    Convert list of jawi strings to rumi strings.\n",
    "    'ايسو بيل تنب دباوا ك كابينيت - صيفالدين' -> 'isu bil tnb dibawa ke kabinet - saifuddin'\n",
    "\n",
    "    Parameters\n",
    "    ----------\n",
    "    strings : List[str]\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    result: List[str]\n",
    "    \"\"\"\n",
    "    return self._greedy_decoder(strings)\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "strings = ['د لابوان ابفچ.',\n",
    " 'سبلومڽ لبيه باڽق جوملهڽ.',\n",
    " 'دان ممرلوكن ڤمبلاان.',\n",
    " 'يڠ لاين.',\n",
    " 'كريتا ڤروندا درڤد بالاي ڤوليس باچوق.',\n",
    " 'سلڤس ٢٨ ڤوسيڠن رونديڠن دان ١٨ مشوارت منتري سلاما كيرا-كيرا توجوه تاهون، رونديڠن ايت',\n",
    " 'ڤنجاڬ ڤرلو فهم دان اد علمو اوروس ورڬ امس، ايلق ڽاڽوق لبيه تروق.',\n",
    " 'ڬوندڠ اداله تيدق بنر، كات كمنترين ڤرتانين دان ايندوستري اساس تاني ﴿موا﴾.',\n",
    " 'بلياو ﴿ازهم﴾ داتڠ ك فام ڤد خميس لڤس برجومڤا دڠن ستياءوسها اڬوڠ فام ﴿ستوارت راماليڠام﴾ سلڤس ايت كلوار دڠن كڽاتأن',\n",
    " 'يڠ توروت حاضر، تيمبالن ڤردان منتري، داتوق سري در وان عزيزه وان اسماعيل دان منتري كابينيت.']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['di labuan ibfc.',\n",
       " 'sebelumnya lebih banyak jumlahnya.',\n",
       " 'dan memerlukan pembelaan. dan memerlukan pembelaan.',\n",
       " 'yang lain.',\n",
       " 'kereta peronda daripada balai polis bachok.',\n",
       " 'selepas 28 pusingan rundingan dan 18 mesyuarat menteri selama kira-kira tujuh tahun, rundingan itu',\n",
       " 'penjaga perlu faham dan ada ilmu urus warga emas, elak nyanyuk lebih teruk.',\n",
       " 'gondang adalah tidak benar, kata kementerian pertanian dan industri asas tani (moa).',\n",
       " 'beliau (izham) datang ke fam pada khamis lepas berjumpa dengan setiausaha agung fam (stuart ramalingam) selepas itu keluar dengan kenyataan',\n",
       " 'yang turut hadir, timbalan perdana menteri, datuk seri dr wan azizah wan ismail dan menteri kabinet.']"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.greedy_decoder(strings)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['di labuan ibfc.',\n",
       " 'sebelumnya lebih banyak jumlahnya.',\n",
       " 'dan memerlukan pembelaan. dan memerlukan pembelaan.',\n",
       " 'yang lain.',\n",
       " 'kereta peronda daripada balai polis bachok.',\n",
       " 'selepas 28 pusingan rundingan dan 18 mesyuarat menteri selama kira-kira tujuh tahun, rundingan itu',\n",
       " 'penjaga perlu faham dan ada ilmu urus warga emas, elak nyanyuk lebih teruk.',\n",
       " 'gondang adalah tidak benar, kata kementerian pertanian dan industri asas tani (moa).',\n",
       " 'beliau (izham) datang ke fam pada khamis lepas berjumpa dengan setiausaha agung fam (stuart ramalingam) selepas itu keluar dengan kenyataan',\n",
       " 'yang turut hadir, timbalan perdana menteri, datuk seri dr wan azizah wan ismail dan menteri kabinet.']"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quantized_model.greedy_decoder(strings)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "string = 'ساي سوك ماكن ايم'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['saya suka makan ayam']"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.greedy_decoder([string])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['saya suka makan ayam']"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quantized_model.greedy_decoder([string])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.7"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}