Upload Attention_Simple_Indo_Evaluation.ipynb

fine tuning/Attention_Simple_Indo_Evaluation.ipynb

@@ -0,0 +1,587 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "pycharm": {
+     "metadata": false,
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2.0.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pickle\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "from torch import optim\n",
+    "import torch.nn.functional as F\n",
+    "from torch.autograd import Variable\n",
+    "from nltk import word_tokenize\n",
+    "\n",
+    "MIN_LENGTH = 4\n",
+    "MAX_LENGTH = 102\n",
+    "START, START_IDX = '<s>',  0\n",
+    "END, END_IDX = '</s>', 1\n",
+    "UNK, UNK_IDX = 'UNK', 2\n",
+    "\n",
+    "SOS_token = START_IDX\n",
+    "EOS_token = END_IDX\n",
+    "\n",
+    "print(torch.__version__)\n",
+    "\n",
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "use_cuda = torch.cuda.is_available()\n",
+    "\n",
+    "# Lets load our dictionaries.\n",
+    "f_eng = open('vocabs/simple_english_vocab.Dictionary.pkl', 'rb')\n",
+    "english_vocab = pickle.load(f_eng)\n",
+    "\n",
+    "f_ind = open('vocabs/simple_indo_vocab.Dictionary.pkl', 'rb')\n",
+    "indo_vocab = pickle.load(f_ind)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [],
+   "source": [
+    "class EncoderRNN(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size):\n",
+    "        super(EncoderRNN, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "\n",
+    "        self.embedding = nn.Embedding(input_size, hidden_size)\n",
+    "        self.gru = nn.GRU(hidden_size, hidden_size)\n",
+    "\n",
+    "    def forward(self, input, hidden):\n",
+    "        embedded = self.embedding(input).view(1, 1, -1)\n",
+    "        output = embedded\n",
+    "        output, hidden = self.gru(output, hidden)\n",
+    "        return output, hidden\n",
+    "\n",
+    "    def initHidden(self):\n",
+    "        return torch.zeros(1, 1, self.hidden_size, device=device)\n",
+    "\n",
+    "class AttnDecoderRNN(nn.Module):\n",
+    "    def __init__(self, hidden_size, output_size, dropout_p=0.1, max_length=MAX_LENGTH):  # Add max_length as a parameter\n",
+    "        super(AttnDecoderRNN, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "        self.output_size = output_size\n",
+    "        self.dropout_p = dropout_p\n",
+    "        self.max_length = max_length  # Update max_length\n",
+    "\n",
+    "        self.embedding = nn.Embedding(self.output_size, self.hidden_size)\n",
+    "        self.attn = nn.Linear(self.hidden_size * 2, self.max_length)  # Update attention layer\n",
+    "        self.attn_combine = nn.Linear(self.hidden_size * 2, self.hidden_size)\n",
+    "        self.dropout = nn.Dropout(self.dropout_p)\n",
+    "        self.gru = nn.GRU(self.hidden_size, self.hidden_size)\n",
+    "        self.out = nn.Linear(self.hidden_size, self.output_size)\n",
+    "\n",
+    "    def forward(self, input, hidden, encoder_outputs):\n",
+    "        embedded = self.embedding(input).view(1, 1, -1)\n",
+    "        embedded = self.dropout(embedded)\n",
+    "\n",
+    "        attn_weights = F.softmax(\n",
+    "            self.attn(torch.cat((embedded[0], hidden[0]), 1)), dim=1)\n",
+    "        attn_applied = torch.bmm(attn_weights.unsqueeze(0),\n",
+    "                                 encoder_outputs.unsqueeze(0))\n",
+    "\n",
+    "        output = torch.cat((embedded[0], attn_applied[0]), 1)\n",
+    "        output = self.attn_combine(output).unsqueeze(0)\n",
+    "\n",
+    "        output = F.relu(output)\n",
+    "        output, hidden = self.gru(output, hidden)\n",
+    "\n",
+    "        output = F.log_softmax(self.out(output[0]), dim=1)\n",
+    "        return output, hidden, attn_weights\n",
+    "\n",
+    "    def initHidden(self):\n",
+    "        return torch.zeros(1, 1, self.hidden_size, device=device)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [],
+   "source": [
+    "#mengonversi kalimat menjadi vektor \n",
+    "def vectorize_sent(sent, vocab):\n",
+    "    return vocab.doc2idx([START] + word_tokenize(sent.lower()) + [END], unknown_word_index=2)\n",
+    "\n",
+    "#mengonversi vektor ke dalam bentuk tensor pytorch untuk input model \n",
+    "def variable_from_sent(sent, vocab):\n",
+    "    vsent = vectorize_sent(sent, vocab)\n",
+    "    # print(vsent)\n",
+    "    result = Variable(torch.LongTensor(vsent).view(-1, 1))\n",
+    "    # print(result)\n",
+    "    return result.cuda() if use_cuda else result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [],
+   "source": [
+    "#lakukan evaluasi pada model\n",
+    "def evaluate(encoder, decoder, sentence, max_length=MAX_LENGTH):\n",
+    "    with torch.no_grad():\n",
+    "        # input_tensor = tensorFromSentence(input_lang, sentence)\n",
+    "        input_tensor = variable_from_sent(sentence, english_vocab)\n",
+    "        input_length = input_tensor.size()[0]\n",
+    "        encoder_hidden = encoder.initHidden()\n",
+    "\n",
+    "        encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)\n",
+    "\n",
+    "        for ei in range(input_length):\n",
+    "            encoder_output, encoder_hidden = encoder(input_tensor[ei],\n",
+    "                                                     encoder_hidden)\n",
+    "            encoder_outputs[ei] += encoder_output[0, 0]\n",
+    "\n",
+    "        decoder_input = torch.tensor([[SOS_token]], device=device)  # SOS\n",
+    "\n",
+    "        decoder_hidden = encoder_hidden\n",
+    "\n",
+    "        decoded_words = []\n",
+    "        decoder_attentions = torch.zeros(max_length, max_length)\n",
+    "\n",
+    "        for di in range(max_length):\n",
+    "            decoder_output, decoder_hidden, decoder_attention = decoder(\n",
+    "                decoder_input, decoder_hidden, encoder_outputs)\n",
+    "            decoder_attentions[di] = decoder_attention.data\n",
+    "            topv, topi = decoder_output.data.topk(1)\n",
+    "            if topi.item() == EOS_token:\n",
+    "                decoded_words.append('</s>')\n",
+    "                break\n",
+    "            else:\n",
+    "                decoded_words.append(indo_vocab.id2token[topi.item()])\n",
+    "\n",
+    "            decoder_input = topi.squeeze().detach()\n",
+    "\n",
+    "        return decoded_words, decoder_attentions[:di + 1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [],
+   "source": [
+    "hidden_size = 512\n",
+    "encoder = EncoderRNN(len(english_vocab), hidden_size).to(device)\n",
+    "attn_decoder = AttnDecoderRNN(hidden_size, len(indo_vocab), dropout_p=0.5).to(device)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "pycharm": {}
+   },
+   "source": [
+    "### Load a network weight snapshot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "EncoderRNN(\n",
+       "  (embedding): Embedding(18990, 512)\n",
+       "  (gru): GRU(512, 512)\n",
+       ")"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ENCODER_PATH = 'results/encoder-{}.pth'\n",
+    "DECODER_PATH = 'results/decoder-{}.pth'\n",
+    "\n",
+    "EPOCH_NO = 75000\n",
+    "\n",
+    "encoder.load_state_dict(torch.load(ENCODER_PATH.format(EPOCH_NO), map_location=device))\n",
+    "encoder.eval()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AttnDecoderRNN(\n",
+       "  (embedding): Embedding(18722, 512)\n",
+       "  (attn): Linear(in_features=1024, out_features=102, bias=True)\n",
+       "  (attn_combine): Linear(in_features=1024, out_features=512, bias=True)\n",
+       "  (dropout): Dropout(p=0.5, inplace=False)\n",
+       "  (gru): GRU(512, 512)\n",
+       "  (out): Linear(in_features=512, out_features=18722, bias=True)\n",
+       ")"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "attn_decoder.load_state_dict(torch.load(DECODER_PATH.format(EPOCH_NO),map_location=device))\n",
+    "attn_decoder.eval()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "> Tom is a good man\n",
+      "< <s> tom adalah seorang yang baik . </s>\n"
+     ]
+    }
+   ],
+   "source": [
+    "input_sentence = \"Tom is a good man\"\n",
+    "output_words, attentions = evaluate(encoder, attn_decoder, input_sentence)\n",
+    "output_sentence = ' '.join(output_words)\n",
+    "print('>', input_sentence)\n",
+    "print('<', output_sentence)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "pycharm": {}
+   },
+   "source": [
+    "### Load an array of network weights snapshots"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[-1]\n"
+     ]
+    }
+   ],
+   "source": [
+    "test_id = english_vocab.doc2idx([\"liling\"])\n",
+    "print(test_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [],
+   "source": [
+    "ENCODER_PATH = 'results/encoder-{}.pth'\n",
+    "DECODER_PATH = 'results/decoder-{}.pth'\n",
+    "\n",
+    "EPOCH_NO = [75000]\n",
+    "\n",
+    "def load_weights(encoder, decoder, epoch_no, device):\n",
+    "    encoder.load_state_dict(torch.load(ENCODER_PATH.format(epoch_no),map_location=device))\n",
+    "    decoder.load_state_dict(torch.load(DECODER_PATH.format(epoch_no),map_location=device))\n",
+    "    return encoder, decoder\n",
+    "\n",
+    "\n",
+    "def input_validation(input_text, english_vocab):\n",
+    "    max_words_required = MAX_LENGTH - 2\n",
+    "    min_words_required = MIN_LENGTH\n",
+    "    input_tokenized = word_tokenize(input_text.lower())\n",
+    "    final_text = None\n",
+    "    message = \"\"\n",
+    "    if not min_words_required <= len(input_tokenized) <= max_words_required:\n",
+    "        message = \"The input sentence should be between {} and {} words\".format(MIN_LENGTH, MAX_LENGTH - 2)\n",
+    "    else:\n",
+    "        input_ids = english_vocab.doc2idx(input_tokenized)\n",
+    "        unknown_tokens = []\n",
+    "        for key, val in enumerate(input_ids):\n",
+    "            if val == -1:\n",
+    "                unknown_token = input_tokenized[key]\n",
+    "                unknown_tokens.append(unknown_token)\n",
+    "                input_tokenized[key] = UNK.lower()\n",
+    "                print(\"'{}' is not found in the english corpus\".format(unknown_token))\n",
+    "        final_text = \" \".join(input_tokenized)\n",
+    "    return final_text, message\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.Requirement already satisfied: ipywidgets in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (8.0.4)\n",
+      "Requirement already satisfied: ipykernel>=4.5.1 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipywidgets) (6.25.0)\n",
+      "Requirement already satisfied: ipython>=6.1.0 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipywidgets) (8.12.2)\n",
+      "Requirement already satisfied: traitlets>=4.3.1 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipywidgets) (5.7.1)\n",
+      "Requirement already satisfied: widgetsnbextension~=4.0 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipywidgets) (4.0.5)\n",
+      "Requirement already satisfied: jupyterlab-widgets~=3.0 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipywidgets) (3.0.5)\n",
+      "Requirement already satisfied: comm>=0.1.1 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (0.1.2)\n",
+      "Requirement already satisfied: debugpy>=1.6.5 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (1.6.7)\n",
+      "Requirement already satisfied: jupyter-client>=6.1.12 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (7.4.9)\n",
+      "Requirement already satisfied: jupyter-core!=5.0.*,>=4.12 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (5.3.0)\n",
+      "Requirement already satisfied: matplotlib-inline>=0.1 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (0.1.6)\n",
+      "Requirement already satisfied: nest-asyncio in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (1.5.6)\n",
+      "Requirement already satisfied: packaging in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (23.2)\n",
+      "Requirement already satisfied: psutil in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (5.9.0)\n",
+      "Requirement already satisfied: pyzmq>=20 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (23.2.0)\n",
+      "Requirement already satisfied: tornado>=6.1 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipykernel>=4.5.1->ipywidgets) (6.3.2)\n",
+      "Requirement already satisfied: backcall in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (0.2.0)\n",
+      "Requirement already satisfied: decorator in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (5.1.1)\n",
+      "Requirement already satisfied: jedi>=0.16 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (0.18.1)\n",
+      "Requirement already satisfied: pickleshare in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (0.7.5)\n",
+      "Requirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (3.0.36)\n",
+      "Requirement already satisfied: pygments>=2.4.0 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (2.15.1)\n",
+      "Requirement already satisfied: stack-data in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (0.2.0)\n",
+      "Requirement already satisfied: colorama in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from ipython>=6.1.0->ipywidgets) (0.4.6)\n",
+      "Requirement already satisfied: parso<0.9.0,>=0.8.0 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from jedi>=0.16->ipython>=6.1.0->ipywidgets) (0.8.3)\n",
+      "Requirement already satisfied: entrypoints in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets) (0.4)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets) (2.8.2)\n",
+      "Requirement already satisfied: platformdirs>=2.5 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from jupyter-core!=5.0.*,>=4.12->ipykernel>=4.5.1->ipywidgets) (3.10.0)\n",
+      "Requirement already satisfied: pywin32>=300 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from jupyter-core!=5.0.*,>=4.12->ipykernel>=4.5.1->ipywidgets) (305.1)\n",
+      "Requirement already satisfied: wcwidth in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython>=6.1.0->ipywidgets) (0.2.5)\n",
+      "Requirement already satisfied: executing in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (0.8.3)\n",
+      "Requirement already satisfied: asttokens in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.0.5)\n",
+      "Requirement already satisfied: pure-eval in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (0.2.2)\n",
+      "Requirement already satisfied: six>=1.5 in c:\\users\\elisa\\anaconda3\\envs\\deeplearning\\lib\\site-packages (from python-dateutil>=2.8.2->jupyter-client>=6.1.12->ipykernel>=4.5.1->ipywidgets) (1.16.0)\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Please uncomment below line to use Jupyter widgets\n",
+    "%pip install ipywidgets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "pycharm": {}
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3161da6ac5e34bc98df35cb77a0f9c3c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Text(value='', description='English:', placeholder='Type something')"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c32657456c0e4b258c1fb843c2821a57",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Button(button_style='info', description='Translate', icon='check', style=ButtonStyle(), tooltip='Translate')"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import ipywidgets as widgets\n",
+    "\n",
+    "input_text = widgets.Text(\n",
+    "    value='',\n",
+    "    placeholder='Type something',\n",
+    "    description='English:',\n",
+    "    disabled=False\n",
+    ")\n",
+    "\n",
+    "button = widgets.Button(\n",
+    "    description='Translate',\n",
+    "    disabled=False,\n",
+    "    button_style='info', # 'success', 'info', 'warning', 'danger' or ''\n",
+    "    tooltip='Translate',\n",
+    "    icon='check'\n",
+    ")\n",
+    "\n",
+    "def on_button_clicked(b):\n",
+    "    eng2indo_translation(input_text.value, encoder, attn_decoder, english_vocab)\n",
+    "\n",
+    "button.on_click(on_button_clicked)\n",
+    "\n",
+    "display(input_text)\n",
+    "display(button)\n",
+    "\n",
+    "def eng2indo_translation(text, encoder, decoder, english_vocab):\n",
+    "    sentences = text.split('.')  # Split input text into sentences based on \".\"\n",
+    "    translated_sentences = []\n",
+    "\n",
+    "    for sentence in sentences:\n",
+    "        final_text, message = input_validation(sentence.strip(), english_vocab)\n",
+    "\n",
+    "        if final_text:\n",
+    "            print('>', sentence)\n",
+    "            print('>>', final_text)\n",
+    "\n",
+    "            for epoch in EPOCH_NO:\n",
+    "                encoder, decoder = load_weights(encoder, decoder, epoch, device)\n",
+    "                output_words, attentions = evaluate(encoder, decoder, final_text)\n",
+    "                output_sentence = ' '.join(output_words).replace('<s>', '').replace('</s>', '')\n",
+    "                translated_sentences.append(output_sentence)\n",
+    "\n",
+    "    # Concatenate translated sentences\n",
+    "    final_output = ' '.join(translated_sentences)\n",
+    "    print(\"Final Translation:\", final_output)\n",
+    "\n",
+    "    if message:\n",
+    "        print(\"Validation Message:\", message)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "> she is standing there \n",
+      ">> she is standing there\n",
+      "Final Translation:  dia ada di sana . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "> he is a bad man \n",
+      ">> he is a bad man\n",
+      "Final Translation:  dia adalah seorang yang yang sangat \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "> he wants to sleep \n",
+      ">> he wants to sleep\n",
+      "Final Translation:  dia ingin tidak lagi . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "'n't' is not found in the english corpus\n",
+      "> i can't see you crying \n",
+      ">> i ca unk see you crying\n",
+      "Final Translation:  aku sudah makan kamu kamu . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "> my dog is running around \n",
+      ">> my dog is running around\n",
+      "Final Translation:  saya saya berada di luar . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "> it is very popular \n",
+      ">> it is very popular\n",
+      "Final Translation:  ini benar benar . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "''s' is not found in the english corpus\n",
+      "> she speaks american english to tom's father \n",
+      ">> she speaks american english to tom unk father\n",
+      "Final Translation:  dia sudah amerika amerika amerika tom telah \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "> please eat lunch in the afternoon \n",
+      ">> please eat lunch in the afternoon\n",
+      "Final Translation:  tolong makan makan di depan . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n",
+      "> i see red roses in the garden \n",
+      ">> i see red roses in the garden\n",
+      "Final Translation:  saya melihat melihat di di taman . \n",
+      "Validation Message: The input sentence should be between 4 and 100 words\n"
+     ]
+    }
+   ],
+   "source": [
+    "eng2indo_translation(\"she is standing there .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"he is a bad man .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"he wants to sleep .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"i can't see you crying .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"my dog is running around .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"it is very popular .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"she speaks american english to tom's father .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"please eat lunch in the afternoon .\", encoder, attn_decoder, english_vocab)\n",
+    "eng2indo_translation(\"i see red roses in the garden .\", encoder, attn_decoder, english_vocab)"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  },
+  "stem_cell": {
+   "cell_type": "raw",
+   "metadata": {
+    "pycharm": {
+     "metadata": false
+    }
+   },
+   "source": ""
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}