Upload 29 files

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Machine_Translation-main/english_to_french_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
 Machine_Translation-main/transformer_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+Task[[:space:]]2/english_to_french_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+Task[[:space:]]2/transformer_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

Task 2/Eng_French.ipynb

@@ -0,0 +1,868 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "# Machine Translation Project (English to French)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import collections\n",
+    "import numpy as np\n",
+    "import json\n",
+    "\n",
+    "from keras.preprocessing.text import Tokenizer\n",
+    "from keras.utils import pad_sequences\n",
+    "from keras.models import Model, Sequential\n",
+    "from keras.layers import Input, Dense, Embedding, GRU, LSTM, Bidirectional, Dropout, Activation, TimeDistributed, RepeatVector\n",
+    "from keras.optimizers import Adam\n",
+    "from keras.losses import sparse_categorical_crossentropy"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Verify access to the GPU"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[name: \"/device:CPU:0\"\n",
+      "device_type: \"CPU\"\n",
+      "memory_limit: 268435456\n",
+      "locality {\n",
+      "}\n",
+      "incarnation: 8951901467623568752\n",
+      "xla_global_id: -1\n",
+      ", name: \"/device:GPU:0\"\n",
+      "device_type: \"GPU\"\n",
+      "memory_limit: 1733715559\n",
+      "locality {\n",
+      "  bus_id: 1\n",
+      "  links {\n",
+      "  }\n",
+      "}\n",
+      "incarnation: 7542354691675806642\n",
+      "physical_device_desc: \"device: 0, name: NVIDIA GeForce RTX 2050, pci bus id: 0000:01:00.0, compute capability: 8.6\"\n",
+      "xla_global_id: 416903419\n",
+      "]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.python.client import device_lib\n",
+    "print(device_lib.list_local_devices())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Dataset\n",
+    "For our machine translation project, we opt for a dataset featuring a limited vocabulary, specifically designed to facilitate a more manageable and efficient training process. Unlike the extensive [WMT](http://www.statmt.org/) datasets, our chosen dataset ensures a quicker training time and demands fewer computational resources. This strategic decision aims to balance the learning experience while still achieving meaningful results within practical time constraints.\n",
+    "### Load Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_data(path):\n",
+    "    input_file = path\n",
+    "    with open(input_file, \"r\") as f:\n",
+    "        data = f.read()\n",
+    "    return data.split('\\n')\n",
+    "\n",
+    "english_sentences = load_data('data/english')\n",
+    "french_sentences = load_data('data/french')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sample Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['new jersey is sometimes quiet during autumn , and it is snowy in april .',\n",
+       " 'the united states is usually chilly during july , and it is usually freezing in november .',\n",
+       " 'california is usually quiet during march , and it is usually hot in june .',\n",
+       " 'the united states is sometimes mild during june , and it is cold in september .',\n",
+       " 'your least liked fruit is the grape , but my least liked is the apple .']"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "english_sentences[:5]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "By examining the sentences, it's apparent that they have undergone preprocessing: punctuation has been delimited with spaces, and all the text has been converted to lowercase. This preprocessing serves a crucial purpose in text preparation. Firstly, delimiting punctuation with spaces ensures that each punctuation mark is treated as a separate token, aiding the model in understanding sentence structure. Secondly, converting the entire text to lowercase standardizes the input, preventing the model from distinguishing between words solely based on their casing. This uniformity facilitates more effective training and generalization, enhancing the model's ability to grasp patterns and generate accurate translations."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Structure of the Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1823250 English words.\n",
+      "227 unique English words.\n",
+      "10 Most common words in the English dataset:\n",
+      "\"is\" \",\" \".\" \"in\" \"it\" \"during\" \"the\" \"but\" \"and\" \"sometimes\"\n",
+      "\n",
+      "1961295 French words.\n",
+      "355 unique French words.\n",
+      "10 Most common words in the French dataset:\n",
+      "\"est\" \".\" \",\" \"en\" \"il\" \"les\" \"mais\" \"et\" \"la\" \"parfois\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "english_words_counter = collections.Counter([word for sentence in english_sentences for word in sentence.split()])\n",
+    "french_words_counter = collections.Counter([word for sentence in french_sentences for word in sentence.split()])\n",
+    "\n",
+    "print('{} English words.'.format(len([word for sentence in english_sentences for word in sentence.split()])))\n",
+    "print('{} unique English words.'.format(len(english_words_counter)))\n",
+    "print('10 Most common words in the English dataset:')\n",
+    "print('\"' + '\" \"'.join(list(zip(*english_words_counter.most_common(10)))[0]) + '\"')\n",
+    "\n",
+    "print()\n",
+    "print('{} French words.'.format(len([word for sentence in french_sentences for word in sentence.split()])))\n",
+    "print('{} unique French words.'.format(len(french_words_counter)))\n",
+    "print('10 Most common words in the French dataset:')\n",
+    "print('\"' + '\" \"'.join(list(zip(*french_words_counter.most_common(10)))[0]) + '\"')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Preprocess\n",
+    "1. Tokenize the words into ids\n",
+    "2. Add padding to make all the sequences the same length."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'the': 1, 'quick': 2, 'a': 3, 'brown': 4, 'fox': 5, 'jumps': 6, 'over': 7, 'lazy': 8, 'dog': 9, 'by': 10, 'jove': 11, 'my': 12, 'study': 13, 'of': 14, 'lexicography': 15, 'won': 16, 'prize': 17, 'this': 18, 'is': 19, 'short': 20, 'sentence': 21}\n",
+      "\n",
+      "Sequence 1 in x\n",
+      "  Input:  The quick brown fox jumps over the lazy dog .\n",
+      "  Output: [1, 2, 4, 5, 6, 7, 1, 8, 9]\n",
+      "Sequence 2 in x\n",
+      "  Input:  By Jove , my quick study of lexicography won a prize .\n",
+      "  Output: [10, 11, 12, 2, 13, 14, 15, 16, 3, 17]\n",
+      "Sequence 3 in x\n",
+      "  Input:  This is a short sentence .\n",
+      "  Output: [18, 19, 3, 20, 21]\n"
+     ]
+    }
+   ],
+   "source": [
+    "def tokenize(x):\n",
+    "    tokenizer = Tokenizer()\n",
+    "    tokenizer.fit_on_texts(x)\n",
+    "    return tokenizer.texts_to_sequences(x), tokenizer\n",
+    "\n",
+    "text_sentences = [\n",
+    "    'The quick brown fox jumps over the lazy dog .',\n",
+    "    'By Jove , my quick study of lexicography won a prize .',\n",
+    "    'This is a short sentence .']\n",
+    "\n",
+    "text_tokenized, text_tokenizer = tokenize(text_sentences)\n",
+    "print(text_tokenizer.word_index)\n",
+    "print()\n",
+    "for sample_i, (sent, token_sent) in enumerate(zip(text_sentences, text_tokenized)):\n",
+    "    print('Sequence {} in x'.format(sample_i + 1))\n",
+    "    print('  Input:  {}'.format(sent))\n",
+    "    print('  Output: {}'.format(token_sent))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Sequence 1 in x\n",
+      "  Input:  [1 2 4 5 6 7 1 8 9]\n",
+      "  Output: [1 2 4 5 6 7 1 8 9 0]\n",
+      "Sequence 2 in x\n",
+      "  Input:  [10 11 12  2 13 14 15 16  3 17]\n",
+      "  Output: [10 11 12  2 13 14 15 16  3 17]\n",
+      "Sequence 3 in x\n",
+      "  Input:  [18 19  3 20 21]\n",
+      "  Output: [18 19  3 20 21  0  0  0  0  0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "def pad(x, length=None):\n",
+    "    if length is None:\n",
+    "        length = max([len(sentence) for sentence in x])\n",
+    "    return pad_sequences(x, maxlen=length, padding='post')\n",
+    "\n",
+    "test_pad = pad(text_tokenized)\n",
+    "for sample_i, (token_sent, pad_sent) in enumerate(zip(text_tokenized, test_pad)):\n",
+    "    print('Sequence {} in x'.format(sample_i + 1))\n",
+    "    print('  Input:  {}'.format(np.array(token_sent)))\n",
+    "    print('  Output: {}'.format(pad_sent))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data Preprocessed\n",
+      "Max English sentence length: 15\n",
+      "Max French sentence length: 21\n",
+      "English vocabulary size: 199\n",
+      "French vocabulary size: 344\n"
+     ]
+    }
+   ],
+   "source": [
+    "def preprocess(x,y):\n",
+    "    preprocess_x, x_tk = tokenize(x)\n",
+    "    preprocess_y, y_tk = tokenize(y)\n",
+    "    \n",
+    "    preprocess_x = pad(preprocess_x)\n",
+    "    preprocess_y = pad(preprocess_y)\n",
+    "    \n",
+    "    preprocess_y = preprocess_y.reshape(*preprocess_y.shape, 1)\n",
+    "    \n",
+    "    return preprocess_x, preprocess_y, x_tk, y_tk\n",
+    "\n",
+    "preproc_english_sentences, preproc_french_sentences, english_tokenizer, french_tokenizer = preprocess(english_sentences, french_sentences)\n",
+    "\n",
+    "max_english_sequence_length = preproc_english_sentences.shape[1]\n",
+    "max_french_sequence_length = preproc_french_sentences.shape[1]\n",
+    "english_vocab_size = len(english_tokenizer.word_index)\n",
+    "french_vocab_size = len(french_tokenizer.word_index)\n",
+    "\n",
+    "print('Data Preprocessed')\n",
+    "print(\"Max English sentence length:\", max_english_sequence_length)\n",
+    "print(\"Max French sentence length:\", max_french_sequence_length)\n",
+    "print(\"English vocabulary size:\", english_vocab_size)\n",
+    "print(\"French vocabulary size:\", french_vocab_size)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Models\n",
+    "- Model 1 is a simple RNN\n",
+    "- Model 2 is a Bidirectional RNN\n",
+    "- Model 3 is an Embedding RNN\n",
+    "\n",
+    "### Ids Back to Text\n",
+    "The neural network will be translating the input to words ids, which isn't the final form we want.  We want the French translation.  The function `logits_to_text` will bridge the gab between the logits from the neural network to the French translation.  You'll be using this function to better understand the output of the neural network."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def logits_to_text(logits, tokenizer):\n",
+    "    index_to_words = {id: word for word, id in tokenizer.word_index.items()}\n",
+    "    index_to_words[0] = '<PAD>'\n",
+    "    \n",
+    "    return ' '.join([index_to_words[prediction] for prediction in np.argmax(logits, 1)])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 1: RNN\n",
+    "![RNN](images/rnn.png)\n",
+    "A basic RNN model is a good baseline for sequence data.  In this model, you'll build a RNN that translates English to French."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/20\n",
+      "108/108 [==============================] - 17s 90ms/step - loss: 1.9094 - accuracy: 0.5446 - val_loss: nan - val_accuracy: 0.6307\n",
+      "Epoch 2/20\n",
+      "108/108 [==============================] - 9s 84ms/step - loss: 1.2243 - accuracy: 0.6429 - val_loss: nan - val_accuracy: 0.6716\n",
+      "Epoch 3/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 1.0848 - accuracy: 0.6683 - val_loss: nan - val_accuracy: 0.6864\n",
+      "Epoch 4/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 1.0057 - accuracy: 0.6832 - val_loss: nan - val_accuracy: 0.6927\n",
+      "Epoch 5/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.9484 - accuracy: 0.6931 - val_loss: nan - val_accuracy: 0.7108\n",
+      "Epoch 6/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.9019 - accuracy: 0.7036 - val_loss: nan - val_accuracy: 0.7007\n",
+      "Epoch 7/20\n",
+      "108/108 [==============================] - 9s 84ms/step - loss: 0.8916 - accuracy: 0.6999 - val_loss: nan - val_accuracy: 0.7244\n",
+      "Epoch 8/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.8407 - accuracy: 0.7178 - val_loss: nan - val_accuracy: 0.7567\n",
+      "Epoch 9/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.7807 - accuracy: 0.7405 - val_loss: nan - val_accuracy: 0.7405\n",
+      "Epoch 10/20\n",
+      "108/108 [==============================] - 9s 84ms/step - loss: 0.7474 - accuracy: 0.7496 - val_loss: nan - val_accuracy: 0.7721\n",
+      "Epoch 11/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.7739 - accuracy: 0.7392 - val_loss: nan - val_accuracy: 0.7392\n",
+      "Epoch 12/20\n",
+      "108/108 [==============================] - 9s 84ms/step - loss: 0.7552 - accuracy: 0.7420 - val_loss: nan - val_accuracy: 0.7851\n",
+      "Epoch 13/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.7238 - accuracy: 0.7550 - val_loss: nan - val_accuracy: 0.7937\n",
+      "Epoch 14/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.7126 - accuracy: 0.7568 - val_loss: nan - val_accuracy: 0.7830\n",
+      "Epoch 15/20\n",
+      "108/108 [==============================] - 9s 84ms/step - loss: 0.6838 - accuracy: 0.7650 - val_loss: nan - val_accuracy: 0.7976\n",
+      "Epoch 16/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.6577 - accuracy: 0.7776 - val_loss: nan - val_accuracy: 0.7995\n",
+      "Epoch 17/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.6447 - accuracy: 0.7821 - val_loss: nan - val_accuracy: 0.8072\n",
+      "Epoch 18/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.6309 - accuracy: 0.7858 - val_loss: nan - val_accuracy: 0.8100\n",
+      "Epoch 19/20\n",
+      "108/108 [==============================] - 9s 84ms/step - loss: 0.6073 - accuracy: 0.7930 - val_loss: nan - val_accuracy: 0.8111\n",
+      "Epoch 20/20\n",
+      "108/108 [==============================] - 9s 83ms/step - loss: 0.6100 - accuracy: 0.7912 - val_loss: nan - val_accuracy: 0.8150\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x2573cec49a0>"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def simple_model(input_shape, output_sequence_length, english_vocab_size, french_vocab_size):\n",
+    "    \n",
+    "    #Hyperparameters\n",
+    "    learning_rate = 0.005\n",
+    "    \n",
+    "    # Build the layers\n",
+    "    model = Sequential()\n",
+    "    model.add(GRU(256, input_shape=input_shape[1:], return_sequences=True))\n",
+    "    model.add(TimeDistributed(Dense(1024, activation='relu')))\n",
+    "    model.add(Dropout(0.5))\n",
+    "    model.add(TimeDistributed(Dense(french_vocab_size, activation='softmax')))\n",
+    "    \n",
+    "    # Compile model\n",
+    "    model.compile(loss = sparse_categorical_crossentropy,\n",
+    "                  optimizer = Adam(learning_rate),\n",
+    "                  metrics = ['accuracy'])\n",
+    "    \n",
+    "    return model\n",
+    "\n",
+    "tmp_x = pad(preproc_english_sentences, max_french_sequence_length)\n",
+    "tmp_x = tmp_x.reshape((-1, preproc_french_sentences.shape[-2], 1))\n",
+    "\n",
+    "#Train the neural network\n",
+    "simple_rnn_model = simple_model(\n",
+    "    tmp_x.shape,\n",
+    "    max_french_sequence_length,\n",
+    "    english_vocab_size,\n",
+    "    french_vocab_size)\n",
+    "\n",
+    "simple_rnn_model.fit(tmp_x, preproc_french_sentences, batch_size=1024, epochs=20, validation_split=0.2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Prediciton:\n",
+      "1/1 [==============================] - 0s 259ms/step\n",
+      "new jersey est parfois calme en mois et il est il est en <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>\n",
+      "\n",
+      "Correct Translation:\n",
+      "[\"new jersey est parfois calme pendant l' automne , et il est neigeux en avril .\"]\n",
+      "\n",
+      "Original text:\n",
+      "['new jersey is sometimes quiet during autumn , and it is snowy in april .']\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Print prediction(s)\n",
+    "print(\"Prediciton:\")\n",
+    "print(logits_to_text(simple_rnn_model.predict(tmp_x[:1])[0], french_tokenizer))\n",
+    "\n",
+    "print(\"\\nCorrect Translation:\")\n",
+    "print(french_sentences[:1])\n",
+    "\n",
+    "print('\\nOriginal text:')\n",
+    "print(english_sentences[:1])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 2: Bidirectional RNNs\n",
+    "![RNN](images/bidirectional.png)\n",
+    "One restriction of a RNN is that it can't see the future input, only the past.  This is where bidirectional recurrent neural networks come in.  They are able to see the future data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential_1\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " bidirectional (Bidirectiona  (None, 21, 256)          100608    \n",
+      " l)                                                              \n",
+      "                                                                 \n",
+      " time_distributed_2 (TimeDis  (None, 21, 1024)         263168    \n",
+      " tributed)                                                       \n",
+      "                                                                 \n",
+      " dropout_1 (Dropout)         (None, 21, 1024)          0         \n",
+      "                                                                 \n",
+      " time_distributed_3 (TimeDis  (None, 21, 344)          352600    \n",
+      " tributed)                                                       \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 716,376\n",
+      "Trainable params: 716,376\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n",
+      "None\n",
+      "Epoch 1/20\n",
+      "108/108 [==============================] - 12s 90ms/step - loss: 1.7553 - accuracy: 0.5756 - val_loss: nan - val_accuracy: 0.6505\n",
+      "Epoch 2/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 1.1655 - accuracy: 0.6550 - val_loss: nan - val_accuracy: 0.6802\n",
+      "Epoch 3/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 1.0423 - accuracy: 0.6759 - val_loss: nan - val_accuracy: 0.6903\n",
+      "Epoch 4/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.9663 - accuracy: 0.6880 - val_loss: nan - val_accuracy: 0.7003\n",
+      "Epoch 5/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.9119 - accuracy: 0.6974 - val_loss: nan - val_accuracy: 0.7207\n",
+      "Epoch 6/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.8700 - accuracy: 0.7059 - val_loss: nan - val_accuracy: 0.7287\n",
+      "Epoch 7/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.8359 - accuracy: 0.7129 - val_loss: nan - val_accuracy: 0.7301\n",
+      "Epoch 8/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.8495 - accuracy: 0.7090 - val_loss: nan - val_accuracy: 0.7300\n",
+      "Epoch 9/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.8025 - accuracy: 0.7197 - val_loss: nan - val_accuracy: 0.7386\n",
+      "Epoch 10/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.7839 - accuracy: 0.7228 - val_loss: nan - val_accuracy: 0.7429\n",
+      "Epoch 11/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.7671 - accuracy: 0.7248 - val_loss: nan - val_accuracy: 0.7461\n",
+      "Epoch 12/20\n",
+      "108/108 [==============================] - 9s 86ms/step - loss: 0.7490 - accuracy: 0.7278 - val_loss: nan - val_accuracy: 0.7487\n",
+      "Epoch 13/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.7341 - accuracy: 0.7307 - val_loss: nan - val_accuracy: 0.7473\n",
+      "Epoch 14/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.7183 - accuracy: 0.7363 - val_loss: nan - val_accuracy: 0.7614\n",
+      "Epoch 15/20\n",
+      "108/108 [==============================] - 9s 86ms/step - loss: 0.6998 - accuracy: 0.7427 - val_loss: nan - val_accuracy: 0.7594\n",
+      "Epoch 16/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.7086 - accuracy: 0.7361 - val_loss: nan - val_accuracy: 0.7596\n",
+      "Epoch 17/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.6889 - accuracy: 0.7424 - val_loss: nan - val_accuracy: 0.7679\n",
+      "Epoch 18/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.6780 - accuracy: 0.7493 - val_loss: nan - val_accuracy: 0.7763\n",
+      "Epoch 19/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.6625 - accuracy: 0.7535 - val_loss: nan - val_accuracy: 0.7771\n",
+      "Epoch 20/20\n",
+      "108/108 [==============================] - 9s 85ms/step - loss: 0.6572 - accuracy: 0.7553 - val_loss: nan - val_accuracy: 0.7560\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x2573f78f0a0>"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def bd_model(input_shape, output_sequence_length, english_vocab_size, french_vocab_size):\n",
+    "    \n",
+    "    #Hyperparameters\n",
+    "    learning_rate = 0.005\n",
+    "    \n",
+    "    # Build the layers\n",
+    "    model = Sequential()\n",
+    "    model.add(Bidirectional(GRU(128, return_sequences=True), input_shape=input_shape[1:]))\n",
+    "    model.add(TimeDistributed(Dense(1024, activation='relu')))\n",
+    "    model.add(Dropout(0.5))\n",
+    "    model.add(TimeDistributed(Dense(french_vocab_size, activation='softmax')))\n",
+    "    \n",
+    "    # Compile model\n",
+    "    model.compile(loss = sparse_categorical_crossentropy,\n",
+    "                  optimizer = Adam(learning_rate),\n",
+    "                  metrics = ['accuracy'])\n",
+    "    \n",
+    "    return model\n",
+    "\n",
+    "tmp_x = pad(preproc_english_sentences, max_french_sequence_length)\n",
+    "tmp_x = tmp_x.reshape((-1, preproc_french_sentences.shape[-2], 1))\n",
+    "\n",
+    "# Train the neural network\n",
+    "bd_rnn_model = bd_model(\n",
+    "    tmp_x.shape,\n",
+    "    max_french_sequence_length,\n",
+    "    english_vocab_size,\n",
+    "    french_vocab_size)\n",
+    "\n",
+    "print(bd_rnn_model.summary())\n",
+    "\n",
+    "bd_rnn_model.fit(tmp_x, preproc_french_sentences, batch_size=1024, epochs=20, validation_split=0.2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Prediciton:\n",
+      "1/1 [==============================] - 1s 544ms/step\n",
+      "new jersey est parfois chaud en mois et il et il est en en <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>\n",
+      "\n",
+      "Correct Translation:\n",
+      "[\"new jersey est parfois calme pendant l' automne , et il est neigeux en avril .\"]\n",
+      "\n",
+      "Original text:\n",
+      "['new jersey is sometimes quiet during autumn , and it is snowy in april .']\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Print prediction(s)\n",
+    "print(\"Prediciton:\")\n",
+    "print(logits_to_text(bd_rnn_model.predict(tmp_x[:1])[0], french_tokenizer))\n",
+    "\n",
+    "print(\"\\nCorrect Translation:\")\n",
+    "print(french_sentences[:1])\n",
+    "\n",
+    "print('\\nOriginal text:')\n",
+    "print(english_sentences[:1])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 3: Embedding\n",
+    "![RNN](images/embedding-words.png)\n",
+    "You've turned the words into ids, but there's a better representation of a word.  This is called word embeddings.  An embedding is a vector representation of the word that is close to similar words in n-dimensional space, where the n represents the size of the embedding vectors."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential_2\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " embedding (Embedding)       (None, 21, 256)           50944     \n",
+      "                                                                 \n",
+      " bidirectional_1 (Bidirectio  (None, 21, 512)          789504    \n",
+      " nal)                                                            \n",
+      "                                                                 \n",
+      " time_distributed_4 (TimeDis  (None, 21, 1024)         525312    \n",
+      " tributed)                                                       \n",
+      "                                                                 \n",
+      " dropout_2 (Dropout)         (None, 21, 1024)          0         \n",
+      "                                                                 \n",
+      " time_distributed_5 (TimeDis  (None, 21, 344)          352600    \n",
+      " tributed)                                                       \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 1,718,360\n",
+      "Trainable params: 1,718,360\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n",
+      "None\n",
+      "Epoch 1/20\n",
+      "108/108 [==============================] - 17s 130ms/step - loss: 1.3473 - accuracy: 0.6924 - val_loss: nan - val_accuracy: 0.8697\n",
+      "Epoch 2/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.3152 - accuracy: 0.9003 - val_loss: nan - val_accuracy: 0.9346\n",
+      "Epoch 3/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.1808 - accuracy: 0.9434 - val_loss: nan - val_accuracy: 0.9578\n",
+      "Epoch 4/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.1291 - accuracy: 0.9601 - val_loss: nan - val_accuracy: 0.9702\n",
+      "Epoch 5/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.1022 - accuracy: 0.9688 - val_loss: nan - val_accuracy: 0.9737\n",
+      "Epoch 6/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0854 - accuracy: 0.9739 - val_loss: nan - val_accuracy: 0.9772\n",
+      "Epoch 7/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0763 - accuracy: 0.9767 - val_loss: nan - val_accuracy: 0.9780\n",
+      "Epoch 8/20\n",
+      "108/108 [==============================] - 14s 127ms/step - loss: 0.0658 - accuracy: 0.9798 - val_loss: nan - val_accuracy: 0.9798\n",
+      "Epoch 9/20\n",
+      "108/108 [==============================] - 14s 127ms/step - loss: 0.0604 - accuracy: 0.9815 - val_loss: nan - val_accuracy: 0.9816\n",
+      "Epoch 10/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0572 - accuracy: 0.9825 - val_loss: nan - val_accuracy: 0.9823\n",
+      "Epoch 11/20\n",
+      "108/108 [==============================] - 14s 127ms/step - loss: 0.0511 - accuracy: 0.9842 - val_loss: nan - val_accuracy: 0.9836\n",
+      "Epoch 12/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0519 - accuracy: 0.9840 - val_loss: nan - val_accuracy: 0.9839\n",
+      "Epoch 13/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0494 - accuracy: 0.9850 - val_loss: nan - val_accuracy: 0.9813\n",
+      "Epoch 14/20\n",
+      "108/108 [==============================] - 14s 127ms/step - loss: 0.0499 - accuracy: 0.9847 - val_loss: nan - val_accuracy: 0.9837\n",
+      "Epoch 15/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0471 - accuracy: 0.9856 - val_loss: nan - val_accuracy: 0.9838\n",
+      "Epoch 16/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0411 - accuracy: 0.9874 - val_loss: nan - val_accuracy: 0.9843\n",
+      "Epoch 17/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0378 - accuracy: 0.9883 - val_loss: nan - val_accuracy: 0.9851\n",
+      "Epoch 18/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0368 - accuracy: 0.9886 - val_loss: nan - val_accuracy: 0.9853\n",
+      "Epoch 19/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0386 - accuracy: 0.9883 - val_loss: nan - val_accuracy: 0.9845\n",
+      "Epoch 20/20\n",
+      "108/108 [==============================] - 14s 126ms/step - loss: 0.0459 - accuracy: 0.9863 - val_loss: nan - val_accuracy: 0.9843\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x2573f340d90>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def bidirectional_embed_model(input_shape, output_sequence_length, english_vocab_size, french_vocab_size):\n",
+    "    \n",
+    "    # Hyperparameters\n",
+    "    learning_rate = 0.005\n",
+    "    \n",
+    "    # Build the layers\n",
+    "    model = Sequential()\n",
+    "    model.add(Embedding(english_vocab_size, 256, input_length=input_shape[1], input_shape=input_shape[1:]))\n",
+    "    model.add(Bidirectional(GRU(256, return_sequences=True)))\n",
+    "    model.add(TimeDistributed(Dense(1024, activation='relu')))\n",
+    "    model.add(Dropout(0.5))\n",
+    "    model.add(TimeDistributed(Dense(french_vocab_size, activation='softmax')))\n",
+    "    \n",
+    "    # Compile model\n",
+    "    model.compile(loss = sparse_categorical_crossentropy,\n",
+    "                  optimizer = Adam(learning_rate),\n",
+    "                  metrics = ['accuracy'])\n",
+    "    \n",
+    "    return model\n",
+    "\n",
+    "tmp_x = pad(preproc_english_sentences, max_french_sequence_length)\n",
+    "tmp_x = tmp_x.reshape((-1, preproc_french_sentences.shape[-2]))\n",
+    "\n",
+    "# Build the model\n",
+    "embed_rnn_model = bidirectional_embed_model(\n",
+    "    tmp_x.shape,\n",
+    "    max_french_sequence_length,\n",
+    "    english_vocab_size,\n",
+    "    french_vocab_size)\n",
+    "\n",
+    "print(embed_rnn_model.summary())\n",
+    "\n",
+    "embed_rnn_model.fit(tmp_x, preproc_french_sentences, batch_size=1024, epochs=20, validation_split=0.2)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Prediciton:\n",
+      "1/1 [==============================] - 0s 410ms/step\n",
+      "new jersey est parfois calme pendant l' automne et il est neigeux en avril <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>\n",
+      "\n",
+      "Correct Translation:\n",
+      "[\"new jersey est parfois calme pendant l' automne , et il est neigeux en avril .\"]\n",
+      "\n",
+      "Original text:\n",
+      "['new jersey is sometimes quiet during autumn , and it is snowy in april .']\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Print prediction(s)\n",
+    "print(\"Prediciton:\")\n",
+    "print(logits_to_text(embed_rnn_model.predict(tmp_x[:1])[0], french_tokenizer))\n",
+    "\n",
+    "print(\"\\nCorrect Translation:\")\n",
+    "print(french_sentences[:1])\n",
+    "\n",
+    "print('\\nOriginal text:')\n",
+    "print(english_sentences[:1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:absl:Found untraced functions such as gru_cell_5_layer_call_fn, gru_cell_5_layer_call_and_return_conditional_losses, gru_cell_6_layer_call_fn, gru_cell_6_layer_call_and_return_conditional_losses while saving (showing 4 of 4). These functions will not be directly callable after loading.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Assets written to: english_to_french_model\\assets\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Assets written to: english_to_french_model\\assets\n"
+     ]
+    }
+   ],
+   "source": [
+    "embed_rnn_model.save('english_to_french_model')\n",
+    "# Serialize English Tokenizer to JSON\n",
+    "with open('english_tokenizer.json', 'w', encoding='utf8') as f:\n",
+    "    f.write(json.dumps(english_tokenizer.to_json(), ensure_ascii=False))\n",
+    "    \n",
+    "# Serialize French Tokenizer to JSON\n",
+    "with open('french_tokenizer.json', 'w', encoding='utf8') as f:\n",
+    "    f.write(json.dumps(french_tokenizer.to_json(), ensure_ascii=False))\n",
+    "    \n",
+    "# Save max lengths\n",
+    "max_french_sequence_length_json = max_french_sequence_length\n",
+    "with open('sequence_length.json', 'w', encoding='utf8') as f:\n",
+    "    f.write(json.dumps(max_french_sequence_length_json, ensure_ascii=False))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

Task 2/Eng_Spanish.ipynb

@@ -0,0 +1,782 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Machine Translation Project (English to Spanish)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pathlib\n",
+    "import random\n",
+    "import string\n",
+    "import tensorflow.strings as tf_strings\n",
+    "import tensorflow.data as tf_data\n",
+    "import re\n",
+    "from keras.layers import TextVectorization\n",
+    "import keras\n",
+    "import tensorflow as tf\n",
+    "from keras import layers\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Verify access to the GPU"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[name: \"/device:CPU:0\"\n",
+      "device_type: \"CPU\"\n",
+      "memory_limit: 268435456\n",
+      "locality {\n",
+      "}\n",
+      "incarnation: 16791471205212918184\n",
+      "xla_global_id: -1\n",
+      ", name: \"/device:GPU:0\"\n",
+      "device_type: \"GPU\"\n",
+      "memory_limit: 1733715559\n",
+      "locality {\n",
+      "  bus_id: 1\n",
+      "  links {\n",
+      "  }\n",
+      "}\n",
+      "incarnation: 6643307082616730570\n",
+      "physical_device_desc: \"device: 0, name: NVIDIA GeForce RTX 2050, pci bus id: 0000:01:00.0, compute capability: 8.6\"\n",
+      "xla_global_id: 416903419\n",
+      "]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.python.client import device_lib\n",
+    "print(device_lib.list_local_devices())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Download and prepare the data\n",
+    "source :\"http://storage.googleapis.com/download.tensorflow.org/data/spa-eng.zip\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Downloading data from http://storage.googleapis.com/download.tensorflow.org/data/spa-eng.zip\n",
+      "2638744/2638744 [==============================] - 11s 4us/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "text_file =  keras.utils.get_file(\n",
+    "    fname = \"spa-eng.zip\",\n",
+    "    origin = \"http://storage.googleapis.com/download.tensorflow.org/data/spa-eng.zip\",\n",
+    "    extract = True,\n",
+    ")\n",
+    "\n",
+    "text_file = pathlib.Path(text_file).parent / \"spa-eng\" / \"spa.txt\"\n",
+    "\n",
+    "with open(text_file, \"r\") as f:\n",
+    "    lines = f.read().split(\"\\n\")[:-1]\n",
+    "    \n",
+    "text_pairs = []\n",
+    "\n",
+    "for line in lines:\n",
+    "    eng, spa = line.split(\"\\t\")\n",
+    "    spa = \"[start] \" + spa + \" [end]\"\n",
+    "    text_pairs.append((eng, spa))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "random.shuffle(text_pairs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "('Please remind me to phone him tomorrow.', '[start] Por favor, recordadme que le llame mañana. [end]')\n",
+      "('These apples taste good.', '[start] Estas manzanas están buenas. [end]')\n",
+      "('Tom is on his own now.', '[start] Tom es independiente ahora. [end]')\n",
+      "('Hey, you want to have a lot of fun? Come with us.', '[start] Oye, ¿quieres entretenerte?, acompáñanos. [end]')\n",
+      "('You have to remain detached.', '[start] Tú tienes que permanecer independiente. [end]')\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in range(5):\n",
+    "    print(text_pairs[i])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Structure of the Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "118964 total pairs\n",
+      "83276 training pairs\n",
+      "17844 validation pairs\n",
+      "17844 test pairs\n"
+     ]
+    }
+   ],
+   "source": [
+    "num_val_samples = int(0.15 * len(text_pairs))\n",
+    "num_train_samples = len(text_pairs) - 2 * num_val_samples\n",
+    "train_pairs = text_pairs[:num_train_samples]\n",
+    "val_pairs = text_pairs[num_train_samples:num_train_samples + num_val_samples]\n",
+    "test_pairs = text_pairs[num_train_samples + num_val_samples:]\n",
+    "\n",
+    "print(f\"{len(text_pairs)} total pairs\")\n",
+    "print(f\"{len(train_pairs)} training pairs\")\n",
+    "print(f\"{len(val_pairs)} validation pairs\")\n",
+    "print(f\"{len(test_pairs)} test pairs\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# parameters\n",
+    "strip_chars = string.punctuation + \"¿\"\n",
+    "strip_chars = strip_chars.replace(\"[\", \"\")\n",
+    "strip_chars = strip_chars.replace(\"]\", \"\")\n",
+    "\n",
+    "vocab_size = 15000\n",
+    "sequence_length = 20\n",
+    "batch_size = 64"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Vectorize the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def custom_standardization(input_string):\n",
+    "    lowercase = tf_strings.lower(input_string)\n",
+    "    return tf_strings.regex_replace(lowercase, f\"[{re.escape(strip_chars)}]\", \"\")\n",
+    "\n",
+    "# vectorization\n",
+    "eng_vectorization = TextVectorization(\n",
+    "    max_tokens = vocab_size,\n",
+    "    output_mode = \"int\",\n",
+    "    output_sequence_length = sequence_length,\n",
+    ")\n",
+    "\n",
+    "spa_vectorization = TextVectorization(\n",
+    "    max_tokens = vocab_size,\n",
+    "    output_mode = \"int\",\n",
+    "    output_sequence_length = sequence_length + 1,\n",
+    "    standardize = custom_standardization,\n",
+    ")\n",
+    "\n",
+    "train_eng_texts = [pair[0] for pair in train_pairs]\n",
+    "train_spa_texts = [pair[1] for pair in train_pairs]\n",
+    "\n",
+    "eng_vectorization.adapt(train_eng_texts)\n",
+    "spa_vectorization.adapt(train_spa_texts)\n",
+    "\n",
+    "#save the vectorization layers\n",
+    "eng_vectorization_config = eng_vectorization.get_config()\n",
+    "eng_vectorization_config.pop('standardize', None)\n",
+    "eng_vocab = eng_vectorization.get_vocabulary()\n",
+    "with open('eng_vectorization_config.json', 'w', encoding='utf-8') as f:\n",
+    "    json.dump(eng_vectorization_config, f)\n",
+    "    \n",
+    "with open('eng_vocab.json', 'w', encoding='utf-8') as f:\n",
+    "    json.dump(eng_vocab, f)\n",
+    "    \n",
+    "spa_vectorization_config = spa_vectorization.get_config()\n",
+    "spa_vectorization_config.pop('standardize', None)\n",
+    "spa_vocab = spa_vectorization.get_vocabulary()\n",
+    "with open('spa_vectorization_config.json', 'w', encoding='utf-8') as f:\n",
+    "    json.dump(spa_vectorization_config, f)\n",
+    "    \n",
+    "with open('spa_vocab.json', 'w', encoding='utf-8') as f:\n",
+    "    json.dump(spa_vocab, f)\n",
+    "    \n",
+    "\n",
+    "def format_dataset(eng, spa):\n",
+    "    eng = eng_vectorization(eng)\n",
+    "    spa = spa_vectorization(spa)\n",
+    "    return (\n",
+    "        {\n",
+    "            \"encoder_inputs\": eng,\n",
+    "            \"decoder_inputs\": spa[:, :-1],\n",
+    "        },\n",
+    "        spa[:, 1:],\n",
+    "    )\n",
+    "    \n",
+    "def make_dataset(pairs):\n",
+    "    eng_texts, spa_texts = zip(*pairs)\n",
+    "    eng_texts = list(eng_texts)\n",
+    "    spa_texts = list(spa_texts)\n",
+    "    dataset = tf_data.Dataset.from_tensor_slices((eng_texts, spa_texts))\n",
+    "    dataset = dataset.batch(batch_size)\n",
+    "    dataset = dataset.map(format_dataset)\n",
+    "    return dataset.cache().shuffle(2048).prefetch(16)\n",
+    "\n",
+    "train_ds = make_dataset(train_pairs)\n",
+    "val_ds = make_dataset(val_pairs)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(64, 20)\n",
+      "(64, 20)\n"
+     ]
+    }
+   ],
+   "source": [
+    "for inputs,targets in train_ds.take(1):\n",
+    "    print(inputs[\"encoder_inputs\"].shape)\n",
+    "    print(targets.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model Architecture\n",
+    "![Encoder-Decoder](images/encoder-decoder-context.png)\n",
+    "![Encoder-Decoder](images/encoder-decoder-translation.png)\n",
+    "![Attention Mechanism](images/attention.png)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Creating an Encoder\n",
+    "class TransformerEncoder(layers.Layer):\n",
+    "    def __init__(self, embed_dim, dense_dim, num_heads, **kwargs):\n",
+    "        super().__init__(**kwargs)\n",
+    "        self.embed_dim = embed_dim\n",
+    "        self.dense_dim = dense_dim\n",
+    "        self.num_heads = num_heads\n",
+    "        self.attention = layers.MultiHeadAttention(\n",
+    "            num_heads = num_heads, key_dim = embed_dim\n",
+    "        )\n",
+    "        self.dense_proj = keras.Sequential(\n",
+    "            [\n",
+    "                layers.Dense(dense_dim, activation = \"relu\"),\n",
+    "                layers.Dense(embed_dim),\n",
+    "            ]\n",
+    "        )\n",
+    "        self.layernorm_1 = layers.LayerNormalization()\n",
+    "        self.layernorm_2 = layers.LayerNormalization()\n",
+    "        self.supports_masking = True\n",
+    "        \n",
+    "    def call(self, inputs, mask=None):\n",
+    "        if mask is not None:\n",
+    "            padding_mask = tf.cast(mask[:, None, :], dtype = tf.int32)\n",
+    "        else:\n",
+    "            padding_mask = None\n",
+    "            \n",
+    "        attention_output = self.attention(\n",
+    "            query = inputs,\n",
+    "            value = inputs,\n",
+    "            key = inputs,\n",
+    "            attention_mask = padding_mask,\n",
+    "        )\n",
+    "        proj_input = self.layernorm_1(inputs + attention_output)\n",
+    "        proj_output = self.dense_proj(proj_input)\n",
+    "        return self.layernorm_2(proj_input + proj_output)\n",
+    "    \n",
+    "    def get_config(self):\n",
+    "        config = super().get_config()\n",
+    "        config.update({\n",
+    "            \"embed_dim\": self.embed_dim,\n",
+    "            \"dense_dim\": self.dense_dim,\n",
+    "            \"num_heads\": self.num_heads,\n",
+    "        })\n",
+    "        return config\n",
+    "    \n",
+    "# Creating a Positional Embedding\n",
+    "class PositionalEmbedding(layers.Layer):\n",
+    "    def __init__(self, sequence_length, vocab_size, embed_dim, **kwargs):\n",
+    "        super().__init__(**kwargs)\n",
+    "        self.token_embeddings = layers.Embedding(\n",
+    "            input_dim = vocab_size, output_dim = embed_dim\n",
+    "        )\n",
+    "        self.position_embeddings = layers.Embedding(\n",
+    "            input_dim = sequence_length, output_dim = embed_dim\n",
+    "        )\n",
+    "        self.sequence_length = sequence_length\n",
+    "        self.vocab_size = vocab_size\n",
+    "        self.embed_dim = embed_dim\n",
+    "        \n",
+    "    def call(self, inputs):\n",
+    "        length = tf.shape(inputs)[-1]\n",
+    "        positions = tf.range(start = 0, limit = length, delta = 1)\n",
+    "        embedded_tokens = self.token_embeddings(inputs)\n",
+    "        embedded_positions = self.position_embeddings(positions)\n",
+    "        return embedded_tokens + embedded_positions\n",
+    "    \n",
+    "    def compute_mask(self, inputs, mask=None):\n",
+    "        if mask is not None:\n",
+    "            return tf.not_equal(inputs, 0)\n",
+    "        else:\n",
+    "            return None\n",
+    "        \n",
+    "    def get_config(self):\n",
+    "        config = super().get_config()\n",
+    "        config.update({\n",
+    "            \"vocab_size\": self.vocab_size,\n",
+    "            \"sequence_length\": self.sequence_length,\n",
+    "            \"embed_dim\": self.embed_dim,\n",
+    "        })\n",
+    "        return config\n",
+    "    \n",
+    "# Creating a Decoder\n",
+    "class TransformerDecoder(layers.Layer):\n",
+    "    def __init__(self, embed_dim, latent_dim, num_heads, **kwargs):\n",
+    "        super().__init__(**kwargs)\n",
+    "        self.embed_dim = embed_dim\n",
+    "        self.latent_dim = latent_dim\n",
+    "        self.num_heads = num_heads\n",
+    "        self.attention_1 = layers.MultiHeadAttention(\n",
+    "            num_heads = num_heads, key_dim = embed_dim\n",
+    "        )\n",
+    "        self.attention_2 = layers.MultiHeadAttention(\n",
+    "            num_heads = num_heads, key_dim = embed_dim\n",
+    "        )\n",
+    "        self.dense_proj = keras.Sequential(\n",
+    "            [\n",
+    "                layers.Dense(latent_dim, activation = \"relu\"),\n",
+    "                layers.Dense(embed_dim),\n",
+    "            ]\n",
+    "        )\n",
+    "        self.layernorm_1 = layers.LayerNormalization()\n",
+    "        self.layernorm_2 = layers.LayerNormalization()\n",
+    "        self.layernorm_3 = layers.LayerNormalization()\n",
+    "        self.supports_masking = True\n",
+    "        \n",
+    "    def call(self, inputs, encoder_outputs, mask=None):\n",
+    "        casual_mask = self.get_causal_attention_mask(inputs)\n",
+    "        if mask is not None:\n",
+    "            padding_mask = tf.cast(mask[:, None, :], dtype = tf.int32)\n",
+    "            padding_mask = tf.minimum(padding_mask, casual_mask)\n",
+    "        else:\n",
+    "            padding_mask = None\n",
+    "            \n",
+    "        attention_output_1 = self.attention_1(\n",
+    "            query = inputs,\n",
+    "            value = inputs,\n",
+    "            key = inputs,\n",
+    "            attention_mask = casual_mask,\n",
+    "        )\n",
+    "        out_1 = self.layernorm_1(inputs + attention_output_1)\n",
+    "        \n",
+    "        attention_output_2 = self.attention_2(\n",
+    "            query = out_1,\n",
+    "            value = encoder_outputs,\n",
+    "            key = encoder_outputs,\n",
+    "            attention_mask = padding_mask,\n",
+    "        )\n",
+    "        \n",
+    "        out_2 = self.layernorm_2(out_1 + attention_output_2)\n",
+    "        proj_output = self.dense_proj(out_2)\n",
+    "        \n",
+    "        return self.layernorm_3(out_2 + proj_output)\n",
+    "    \n",
+    "    def get_causal_attention_mask(self, inputs):\n",
+    "        input_shape = tf.shape(inputs)\n",
+    "        batch_size, sequence_length = input_shape[0], input_shape[1]\n",
+    "        i = tf.range(sequence_length)[:, None]\n",
+    "        j = tf.range(sequence_length)\n",
+    "        mask = tf.cast(i >= j, tf.int32)\n",
+    "        mask = tf.reshape(mask,(1, input_shape[1], input_shape[1]))\n",
+    "        mult = tf.concat(\n",
+    "            [\n",
+    "                tf.expand_dims(batch_size, -1),\n",
+    "                tf.convert_to_tensor([1, 1]),\n",
+    "            ],\n",
+    "            axis = 0,\n",
+    "        )\n",
+    "        return tf.tile(mask, mult)\n",
+    "    \n",
+    "    def get_config(self):\n",
+    "        config = super().get_config()\n",
+    "        config.update({\n",
+    "            \"embed_dim\": self.embed_dim,\n",
+    "            \"latent_dim\": self.latent_dim,\n",
+    "            \"num_heads\": self.num_heads,\n",
+    "        })\n",
+    "        return config\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# define emmbedding dimensions, latent dimensions, and number of heads\n",
+    "embed_dim = 256\n",
+    "latent_dim = 2048\n",
+    "num_heads = 8\n",
+    "\n",
+    "#Encoder\n",
+    "encoder_inputs = keras.Input(shape = (None,), dtype = \"int64\", name = \"encoder_inputs\")\n",
+    "\n",
+    "x = PositionalEmbedding(sequence_length, vocab_size, embed_dim)(encoder_inputs)\n",
+    "\n",
+    "encoder_outputs = TransformerEncoder(embed_dim, latent_dim, num_heads)(x)\n",
+    "\n",
+    "encoder = keras.Model(encoder_inputs, encoder_outputs, name = \"encoder\")\n",
+    "\n",
+    "#Decoder\n",
+    "decoder_inputs = keras.Input(shape = (None,), dtype = \"int64\", name = \"decoder_inputs\")\n",
+    "encoder_seq_inputs = keras.Input(shape = (None, embed_dim), name = \"encoder_seq_inputs\")\n",
+    "\n",
+    "x = PositionalEmbedding(sequence_length, vocab_size, embed_dim)(decoder_inputs)\n",
+    "\n",
+    "x = TransformerDecoder(embed_dim, latent_dim, num_heads)(x, encoder_seq_inputs)\n",
+    "\n",
+    "x = layers.Dropout(0.5)(x)\n",
+    "\n",
+    "decoder_outputs = layers.Dense(vocab_size, activation = \"softmax\")(x)\n",
+    "\n",
+    "decoder = keras.Model([decoder_inputs, encoder_seq_inputs], decoder_outputs, name = \"decoder\")\n",
+    "\n",
+    "# Define the final model\n",
+    "decoder_outputs = decoder([decoder_inputs, encoder_outputs])\n",
+    "\n",
+    "transformer = keras.Model(\n",
+    "    [encoder_inputs, decoder_inputs], decoder_outputs, name = \"transformer\"\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"transformer\"\n",
+      "__________________________________________________________________________________________________\n",
+      " Layer (type)                   Output Shape         Param #     Connected to                     \n",
+      "==================================================================================================\n",
+      " encoder_inputs (InputLayer)    [(None, None)]       0           []                               \n",
+      "                                                                                                  \n",
+      " positional_embedding (Position  (None, None, 256)   3845120     ['encoder_inputs[0][0]']         \n",
+      " alEmbedding)                                                                                     \n",
+      "                                                                                                  \n",
+      " decoder_inputs (InputLayer)    [(None, None)]       0           []                               \n",
+      "                                                                                                  \n",
+      " transformer_encoder (Transform  (None, None, 256)   3155456     ['positional_embedding[0][0]']   \n",
+      " erEncoder)                                                                                       \n",
+      "                                                                                                  \n",
+      " decoder (Functional)           (None, None, 15000)  12959640    ['decoder_inputs[0][0]',         \n",
+      "                                                                  'transformer_encoder[0][0]']    \n",
+      "                                                                                                  \n",
+      "==================================================================================================\n",
+      "Total params: 19,960,216\n",
+      "Trainable params: 19,960,216\n",
+      "Non-trainable params: 0\n",
+      "__________________________________________________________________________________________________\n",
+      "Epoch 1/20\n",
+      "1302/1302 [==============================] - 132s 95ms/step - loss: 1.9854 - accuracy: 0.7200 - val_loss: 1.7019 - val_accuracy: 0.7395\n",
+      "Epoch 2/20\n",
+      "1302/1302 [==============================] - 123s 94ms/step - loss: 1.7172 - accuracy: 0.7499 - val_loss: 1.5479 - val_accuracy: 0.7610\n",
+      "Epoch 3/20\n",
+      "1302/1302 [==============================] - 123s 95ms/step - loss: 1.5636 - accuracy: 0.7712 - val_loss: 1.4142 - val_accuracy: 0.7838\n",
+      "Epoch 4/20\n",
+      "1302/1302 [==============================] - 124s 96ms/step - loss: 1.4229 - accuracy: 0.7906 - val_loss: 1.2981 - val_accuracy: 0.8027\n",
+      "Epoch 5/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 1.3049 - accuracy: 0.8079 - val_loss: 1.2207 - val_accuracy: 0.8173\n",
+      "Epoch 6/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 1.2307 - accuracy: 0.8232 - val_loss: 1.1703 - val_accuracy: 0.8294\n",
+      "Epoch 7/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 1.1852 - accuracy: 0.8348 - val_loss: 1.1304 - val_accuracy: 0.8376\n",
+      "Epoch 8/20\n",
+      "1302/1302 [==============================] - 124s 95ms/step - loss: 1.1455 - accuracy: 0.8431 - val_loss: 1.1064 - val_accuracy: 0.8436\n",
+      "Epoch 9/20\n",
+      "1302/1302 [==============================] - 124s 95ms/step - loss: 1.1154 - accuracy: 0.8496 - val_loss: 1.0878 - val_accuracy: 0.8461\n",
+      "Epoch 10/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 1.0901 - accuracy: 0.8545 - val_loss: 1.0737 - val_accuracy: 0.8498\n",
+      "Epoch 11/20\n",
+      "1302/1302 [==============================] - 124s 95ms/step - loss: 1.0690 - accuracy: 0.8583 - val_loss: 1.0697 - val_accuracy: 0.8472\n",
+      "Epoch 12/20\n",
+      "1302/1302 [==============================] - 124s 95ms/step - loss: 1.0495 - accuracy: 0.8616 - val_loss: 1.0458 - val_accuracy: 0.8543\n",
+      "Epoch 13/20\n",
+      "1302/1302 [==============================] - 124s 95ms/step - loss: 1.0332 - accuracy: 0.8648 - val_loss: 1.0387 - val_accuracy: 0.8548\n",
+      "Epoch 14/20\n",
+      "1302/1302 [==============================] - 123s 95ms/step - loss: 1.0180 - accuracy: 0.8673 - val_loss: 1.0458 - val_accuracy: 0.8550\n",
+      "Epoch 15/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 1.0036 - accuracy: 0.8695 - val_loss: 1.0303 - val_accuracy: 0.8569\n",
+      "Epoch 16/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 0.9891 - accuracy: 0.8720 - val_loss: 1.0184 - val_accuracy: 0.8586\n",
+      "Epoch 17/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 0.9779 - accuracy: 0.8738 - val_loss: 1.0313 - val_accuracy: 0.8567\n",
+      "Epoch 18/20\n",
+      "1302/1302 [==============================] - 126s 96ms/step - loss: 0.9668 - accuracy: 0.8754 - val_loss: 1.0106 - val_accuracy: 0.8614\n",
+      "Epoch 19/20\n",
+      "1302/1302 [==============================] - 125s 96ms/step - loss: 0.9543 - accuracy: 0.8772 - val_loss: 1.0144 - val_accuracy: 0.8598\n",
+      "Epoch 20/20\n",
+      "1302/1302 [==============================] - 124s 95ms/step - loss: 0.9415 - accuracy: 0.8791 - val_loss: 1.0139 - val_accuracy: 0.8617\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x24df73cf5e0>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "epochs = 20\n",
+    "\n",
+    "transformer.summary()\n",
+    "\n",
+    "transformer.compile(\n",
+    "    \"rmsprop\", loss = \"sparse_categorical_crossentropy\", metrics = [\"accuracy\"]\n",
+    ")\n",
+    "\n",
+    "transformer.fit(train_ds, epochs = epochs, validation_data = val_ds)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:absl:Found untraced functions such as embedding_layer_call_fn, embedding_layer_call_and_return_conditional_losses, embedding_1_layer_call_fn, embedding_1_layer_call_and_return_conditional_losses, multi_head_attention_layer_call_fn while saving (showing 5 of 60). These functions will not be directly callable after loading.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Assets written to: transformer_model\\assets\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Assets written to: transformer_model\\assets\n"
+     ]
+    }
+   ],
+   "source": [
+    "transformer.save(\"transformer_model\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "input: a few passengers went on board the plane\n",
+      "translated: [start] unos dos te [UNK] en los años [end]\n",
+      "\n",
+      "input: i think shes an honest woman\n",
+      "translated: [start] creo que es una mujer [UNK] [end]\n",
+      "\n",
+      "input: im old enough to do that on my own\n",
+      "translated: [start] soy lo suficientemente viejo para hacer por mi [end]\n",
+      "\n",
+      "input: youre too drunk to drive\n",
+      "translated: [start] eres demasiado de conducir [end]\n",
+      "\n",
+      "input: id like to go to hawaii\n",
+      "translated: [start] quisiera ir a china [end]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "spa_vocab = spa_vectorization.get_vocabulary()\n",
+    "spa_index_lookup = dict(zip(range(len(spa_vocab)), spa_vocab))\n",
+    "max_decoded_sentence_length = sequence_length\n",
+    "\n",
+    "def decode_sentence(input_sentence):\n",
+    "    tokenized_input_sentence = eng_vectorization([input_sentence])\n",
+    "    decoded_sentence = \"[start]\"\n",
+    "    for i in range(max_decoded_sentence_length):\n",
+    "        tokenized_target_sentence = spa_vectorization([decoded_sentence])[:, :-1]\n",
+    "        predictions = transformer([tokenized_input_sentence, tokenized_target_sentence])\n",
+    "        sampled_token_index = tf.argmax(predictions[0, i, :]).numpy().item(0)\n",
+    "        sampled_token = spa_index_lookup[sampled_token_index]\n",
+    "        decoded_sentence += \" \" + sampled_token\n",
+    "        if sampled_token == \"[end]\":\n",
+    "            break\n",
+    "    return decoded_sentence\n",
+    "\n",
+    "test_eng_texts = [pair[0] for pair in test_pairs]\n",
+    "for _ in range(5):\n",
+    "    input_sentence = random.choice(test_eng_texts)\n",
+    "    input_sentence = input_sentence.lower()\n",
+    "    input_sentence = input_sentence.translate(str.maketrans('', '', strip_chars))\n",
+    "    translated = decode_sentence(input_sentence)\n",
+    "    print(f\"input: {input_sentence}\")\n",
+    "    print(f\"translated: {translated}\")\n",
+    "    print()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: tensorflow in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (2.10.1)Note: you may need to restart the kernel to use updated packages.\n",
+      "\n",
+      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (2.1.0)\n",
+      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (1.6.3)\n",
+      "Requirement already satisfied: flatbuffers>=2.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (24.3.25)\n",
+      "Requirement already satisfied: gast<=0.4.0,>=0.2.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (0.4.0)\n",
+      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (0.2.0)\n",
+      "Requirement already satisfied: h5py>=2.9.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (3.11.0)\n",
+      "Requirement already satisfied: keras-preprocessing>=1.1.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (1.1.2)\n",
+      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (18.1.1)\n",
+      "Requirement already satisfied: numpy>=1.20 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (1.26.4)\n",
+      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (3.3.0)\n",
+      "Requirement already satisfied: packaging in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (24.0)\n",
+      "Requirement already satisfied: protobuf<3.20,>=3.9.2 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (3.19.6)\n",
+      "Requirement already satisfied: setuptools in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (69.5.1)\n",
+      "Requirement already satisfied: six>=1.12.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (1.16.0)\n",
+      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (2.4.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (4.12.2)\n",
+      "Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (1.16.0)\n",
+      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (0.31.0)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (1.64.1)\n",
+      "Requirement already satisfied: tensorboard<2.11,>=2.10 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (2.10.1)\n",
+      "Requirement already satisfied: tensorflow-estimator<2.11,>=2.10.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (2.10.0)\n",
+      "Requirement already satisfied: keras<2.11,>=2.10.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorflow) (2.10.0)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from astunparse>=1.6.0->tensorflow) (0.43.0)\n",
+      "Requirement already satisfied: google-auth<3,>=1.6.3 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (2.30.0)\n",
+      "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (0.4.6)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (3.6)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (2.32.3)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (0.6.1)\n",
+      "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (1.8.1)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from tensorboard<2.11,>=2.10->tensorflow) (3.0.3)\n",
+      "Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.11,>=2.10->tensorflow) (5.3.3)\n",
+      "Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.11,>=2.10->tensorflow) (0.4.0)\n",
+      "Requirement already satisfied: rsa<5,>=3.1.4 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.11,>=2.10->tensorflow) (4.9)\n",
+      "Requirement already satisfied: requests-oauthlib>=0.7.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.11,>=2.10->tensorflow) (2.0.0)\n",
+      "Requirement already satisfied: importlib-metadata>=4.4 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from markdown>=2.6.8->tensorboard<2.11,>=2.10->tensorflow) (7.1.0)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.11,>=2.10->tensorflow) (3.3.2)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.11,>=2.10->tensorflow) (3.7)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.11,>=2.10->tensorflow) (2.2.1)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.11,>=2.10->tensorflow) (2024.6.2)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard<2.11,>=2.10->tensorflow) (2.1.5)\n",
+      "Requirement already satisfied: zipp>=0.5 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.11,>=2.10->tensorflow) (3.19.2)\n",
+      "Requirement already satisfied: pyasn1<0.7.0,>=0.4.6 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.11,>=2.10->tensorflow) (0.6.0)\n",
+      "Requirement already satisfied: oauthlib>=3.0.0 in c:\\users\\prajw\\anaconda3\\envs\\testnullclass\\lib\\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.11,>=2.10->tensorflow) (3.2.2)\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install tensorflow\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Task 2/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Task 2/README.md

@@ -0,0 +1 @@
+# Machine_Translation

Task 2/eng_vectorization_config.json

@@ -0,0 +1 @@
+{"name": "text_vectorization", "trainable": true, "batch_input_shape": [null], "dtype": "string", "max_tokens": 15000, "split": "whitespace", "ngrams": null, "output_mode": "int", "output_sequence_length": 20, "pad_to_max_tokens": false, "sparse": false, "ragged": false, "vocabulary": null, "idf_weights": null}

Task 2/english_to_french_model/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18727f19a8f2e298e734019630e718acf71e07ef341ce0398a88208498c47dfd
+size 21276

Task 2/english_to_french_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0781d40fb91f9326102fd3c6574611bfc035bff26a81a4d69cedf1ef0b0aa1e5
+size 2021585

Task 2/english_to_french_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c3bfe842a940826fd00c874b3f94b44abdf96953f8d695a1caefbfc1ad9608
+size 20633894

Task 2/english_tokenizer.json

@@ -0,0 +1 @@
+"{\"class_name\": \"Tokenizer\", \"config\": {\"num_words\": null, \"filters\": \"!\\\"#$%&()*+,-./:;<=>?@[\\\\]^_`{|}~\\t\\n\", \"lower\": true, \"split\": \" \", \"char_level\": false, \"oov_token\": null, \"document_count\": 137861, \"word_counts\": \"{\\\"new\\\": 12197, \\\"jersey\\\": 11225, \\\"is\\\": 205858, \\\"sometimes\\\": 37746, \\\"quiet\\\": 8693, \\\"during\\\": 74933, \\\"autumn\\\": 9004, \\\"and\\\": 59850, \\\"it\\\": 75137, \\\"snowy\\\": 8898, \\\"in\\\": 75525, \\\"april\\\": 8954, \\\"the\\\": 67628, \\\"united\\\": 11270, \\\"states\\\": 11270, \\\"usually\\\": 37507, \\\"chilly\\\": 8770, \\\"july\\\": 8956, \\\"freezing\\\": 8928, \\\"november\\\": 8951, \\\"california\\\": 11250, \\\"march\\\": 9023, \\\"hot\\\": 8639, \\\"june\\\": 9133, \\\"mild\\\": 8743, \\\"cold\\\": 8878, \\\"september\\\": 8958, \\\"your\\\": 9734, \\\"least\\\": 27564, \\\"liked\\\": 14046, \\\"fruit\\\": 27192, \\\"grape\\\": 4848, \\\"but\\\": 63987, \\\"my\\\": 9700, \\\"apple\\\": 4848, \\\"his\\\": 9700, \\\"favorite\\\": 28332, \\\"orange\\\": 4848, \\\"paris\\\": 11334, \\\"relaxing\\\": 8696, \\\"december\\\": 8945, \\\"busy\\\": 8791, \\\"spring\\\": 9102, \\\"never\\\": 37500, \\\"our\\\": 8932, \\\"lemon\\\": 4848, \\\"january\\\": 9090, \\\"warm\\\": 8890, \\\"lime\\\": 4848, \\\"her\\\": 9700, \\\"banana\\\": 4848, \\\"he\\\": 10786, \\\"saw\\\": 648, \\\"a\\\": 1944, \\\"old\\\": 972, \\\"yellow\\\": 972, \\\"truck\\\": 1944, \\\"india\\\": 11277, \\\"rainy\\\": 8761, \\\"that\\\": 2712, \\\"cat\\\": 192, \\\"was\\\": 1867, \\\"most\\\": 14934, \\\"loved\\\": 14166, \\\"animal\\\": 2304, \\\"dislikes\\\": 7314, \\\"grapefruit\\\": 10692, \\\"limes\\\": 5844, \\\"lemons\\\": 5844, \\\"february\\\": 8942, \\\"china\\\": 10953, \\\"pleasant\\\": 8916, \\\"october\\\": 8910, \\\"wonderful\\\": 8808, \\\"nice\\\": 8984, \\\"summer\\\": 8948, \\\"france\\\": 11170, \\\"may\\\": 8995, \\\"grapes\\\": 5844, \\\"mangoes\\\": 5844, \\\"their\\\": 8932, \\\"mango\\\": 4848, \\\"pear\\\": 4848, \\\"august\\\": 8789, \\\"beautiful\\\": 8915, \\\"apples\\\": 5844, \\\"peaches\\\": 5844, \\\"feared\\\": 768, \\\"shark\\\": 192, \\\"wet\\\": 8726, \\\"dry\\\": 8794, \\\"we\\\": 2532, \\\"like\\\": 4588, \\\"oranges\\\": 5844, \\\"they\\\": 3222, \\\"pears\\\": 5844, \\\"she\\\": 10786, \\\"little\\\": 1016, \\\"red\\\": 972, \\\"winter\\\": 9038, \\\"disliked\\\": 648, \\\"rusty\\\": 972, \\\"car\\\": 1944, \\\"strawberries\\\": 5844, \\\"i\\\": 2664, \\\"strawberry\\\": 4848, \\\"bananas\\\": 5844, \\\"going\\\": 666, \\\"to\\\": 5166, \\\"next\\\": 1666, \\\"plan\\\": 714, \\\"visit\\\": 1224, \\\"elephants\\\": 64, \\\"were\\\": 384, \\\"animals\\\": 768, \\\"are\\\": 870, \\\"likes\\\": 7314, \\\"dislike\\\": 4444, \\\"fall\\\": 9134, \\\"driving\\\": 1296, \\\"peach\\\": 4848, \\\"drives\\\": 648, \\\"blue\\\": 972, \\\"you\\\": 2414, \\\"bird\\\": 192, \\\"horses\\\": 64, \\\"mouse\\\": 192, \\\"went\\\": 378, \\\"last\\\": 781, \\\"horse\\\": 192, \\\"automobile\\\": 1944, \\\"dogs\\\": 64, \\\"white\\\": 972, \\\"elephant\\\": 192, \\\"black\\\": 972, \\\"think\\\": 240, \\\"difficult\\\": 260, \\\"translate\\\": 480, \\\"between\\\": 540, \\\"spanish\\\": 312, \\\"portuguese\\\": 312, \\\"big\\\": 1016, \\\"green\\\": 972, \\\"translating\\\": 300, \\\"fun\\\": 260, \\\"where\\\": 12, \\\"dog\\\": 192, \\\"why\\\": 240, \\\"might\\\": 378, \\\"go\\\": 1386, \\\"this\\\": 768, \\\"drove\\\": 648, \\\"shiny\\\": 972, \\\"sharks\\\": 64, \\\"monkey\\\": 192, \\\"how\\\": 67, \\\"weather\\\": 33, \\\"lion\\\": 192, \\\"plans\\\": 476, \\\"bear\\\": 192, \\\"rabbit\\\": 192, \\\"it's\\\": 240, \\\"chinese\\\": 312, \\\"when\\\": 144, \\\"eiffel\\\": 57, \\\"tower\\\": 57, \\\"did\\\": 204, \\\"grocery\\\": 57, \\\"store\\\": 57, \\\"wanted\\\": 378, \\\"does\\\": 24, \\\"football\\\": 57, \\\"field\\\": 57, \\\"wants\\\": 252, \\\"didn't\\\": 60, \\\"snake\\\": 192, \\\"snakes\\\": 64, \\\"do\\\": 84, \\\"easy\\\": 260, \\\"thinks\\\": 360, \\\"english\\\": 312, \\\"french\\\": 312, \\\"would\\\": 48, \\\"aren't\\\": 36, \\\"cats\\\": 64, \\\"rabbits\\\": 64, \\\"has\\\": 24, \\\"been\\\": 36, \\\"monkeys\\\": 64, \\\"lake\\\": 57, \\\"bears\\\": 64, \\\"school\\\": 57, \\\"birds\\\": 64, \\\"want\\\": 126, \\\"isn't\\\": 24, \\\"lions\\\": 64, \\\"am\\\": 24, \\\"mice\\\": 64, \\\"have\\\": 12}\", \"word_docs\": \"{\\\"april\\\": 8954, \\\"sometimes\\\": 32946, \\\"new\\\": 12197, \\\"autumn\\\": 9004, \\\"it\\\": 75137, \\\"snowy\\\": 8898, \\\"and\\\": 59850, \\\"in\\\": 75525, \\\"quiet\\\": 8693, \\\"is\\\": 104561, \\\"jersey\\\": 11225, \\\"during\\\": 74933, \\\"united\\\": 11270, \\\"states\\\": 11270, \\\"chilly\\\": 8770, \\\"freezing\\\": 8928, \\\"usually\\\": 32846, \\\"november\\\": 8951, \\\"the\\\": 41221, \\\"july\\\": 8956, \\\"march\\\": 9023, \\\"june\\\": 9133, \\\"california\\\": 11250, \\\"hot\\\": 8639, \\\"september\\\": 8958, \\\"mild\\\": 8743, \\\"cold\\\": 8878, \\\"liked\\\": 7446, \\\"grape\\\": 4848, \\\"but\\\": 63987, \\\"least\\\": 14364, \\\"apple\\\": 4848, \\\"my\\\": 9700, \\\"your\\\": 9734, \\\"fruit\\\": 27192, \\\"his\\\": 9700, \\\"favorite\\\": 15132, \\\"orange\\\": 4848, \\\"december\\\": 8945, \\\"relaxing\\\": 8696, \\\"paris\\\": 11334, \\\"spring\\\": 9102, \\\"never\\\": 32834, \\\"busy\\\": 8791, \\\"our\\\": 8932, \\\"lemon\\\": 4848, \\\"warm\\\": 8890, \\\"january\\\": 9090, \\\"lime\\\": 4848, \\\"her\\\": 9700, \\\"banana\\\": 4848, \\\"old\\\": 972, \\\"truck\\\": 1944, \\\"a\\\": 1944, \\\"saw\\\": 648, \\\"he\\\": 10786, \\\"yellow\\\": 972, \\\"india\\\": 11277, \\\"rainy\\\": 8761, \\\"most\\\": 8334, \\\"animal\\\": 2304, \\\"was\\\": 1867, \\\"cat\\\": 192, \\\"that\\\": 2712, \\\"loved\\\": 7566, \\\"grapefruit\\\": 10692, \\\"limes\\\": 5844, \\\"dislikes\\\": 7314, \\\"lemons\\\": 5844, \\\"february\\\": 8942, \\\"pleasant\\\": 8916, \\\"october\\\": 8910, \\\"china\\\": 10953, \\\"wonderful\\\": 8808, \\\"nice\\\": 8984, \\\"summer\\\": 8948, \\\"france\\\": 11170, \\\"may\\\": 8995, \\\"mangoes\\\": 5844, \\\"grapes\\\": 5844, \\\"mango\\\": 4848, \\\"pear\\\": 4848, \\\"their\\\": 8932, \\\"august\\\": 8789, \\\"beautiful\\\": 8915, \\\"apples\\\": 5844, \\\"peaches\\\": 5844, \\\"feared\\\": 768, \\\"shark\\\": 192, \\\"dry\\\": 8794, \\\"wet\\\": 8726, \\\"we\\\": 2532, \\\"like\\\": 4588, \\\"oranges\\\": 5844, \\\"they\\\": 3222, \\\"pears\\\": 5844, \\\"red\\\": 972, \\\"little\\\": 1016, \\\"she\\\": 10786, \\\"winter\\\": 9038, \\\"rusty\\\": 972, \\\"disliked\\\": 648, \\\"car\\\": 1944, \\\"strawberries\\\": 5844, \\\"i\\\": 2664, \\\"strawberry\\\": 4848, \\\"bananas\\\": 5844, \\\"to\\\": 4170, \\\"going\\\": 666, \\\"next\\\": 1666, \\\"visit\\\": 1224, \\\"plan\\\": 714, \\\"animals\\\": 768, \\\"were\\\": 384, \\\"elephants\\\": 64, \\\"are\\\": 870, \\\"likes\\\": 7314, \\\"dislike\\\": 4444, \\\"fall\\\": 9134, \\\"driving\\\": 1296, \\\"peach\\\": 4848, \\\"drives\\\": 648, \\\"blue\\\": 972, \\\"you\\\": 2414, \\\"bird\\\": 192, \\\"horses\\\": 64, \\\"mouse\\\": 192, \\\"went\\\": 378, \\\"last\\\": 781, \\\"horse\\\": 192, \\\"automobile\\\": 1944, \\\"dogs\\\": 64, \\\"white\\\": 972, \\\"elephant\\\": 192, \\\"black\\\": 972, \\\"translate\\\": 480, \\\"think\\\": 240, \\\"portuguese\\\": 312, \\\"difficult\\\": 260, \\\"spanish\\\": 312, \\\"between\\\": 540, \\\"big\\\": 1016, \\\"green\\\": 972, \\\"fun\\\": 260, \\\"translating\\\": 300, \\\"where\\\": 12, \\\"dog\\\": 192, \\\"why\\\": 240, \\\"go\\\": 1386, \\\"might\\\": 378, \\\"this\\\": 768, \\\"drove\\\": 648, \\\"shiny\\\": 972, \\\"sharks\\\": 64, \\\"monkey\\\": 192, \\\"weather\\\": 33, \\\"how\\\": 67, \\\"lion\\\": 192, \\\"plans\\\": 476, \\\"bear\\\": 192, \\\"rabbit\\\": 192, \\\"chinese\\\": 312, \\\"it's\\\": 240, \\\"tower\\\": 57, \\\"when\\\": 144, \\\"eiffel\\\": 57, \\\"grocery\\\": 57, \\\"did\\\": 204, \\\"store\\\": 57, \\\"wanted\\\": 378, \\\"football\\\": 57, \\\"field\\\": 57, \\\"does\\\": 24, \\\"wants\\\": 252, \\\"didn't\\\": 60, \\\"snake\\\": 192, \\\"snakes\\\": 64, \\\"easy\\\": 260, \\\"do\\\": 84, \\\"french\\\": 312, \\\"thinks\\\": 360, \\\"english\\\": 312, \\\"would\\\": 48, \\\"aren't\\\": 36, \\\"cats\\\": 64, \\\"rabbits\\\": 64, \\\"has\\\": 24, \\\"been\\\": 36, \\\"monkeys\\\": 64, \\\"lake\\\": 57, \\\"bears\\\": 64, \\\"school\\\": 57, \\\"birds\\\": 64, \\\"want\\\": 126, \\\"isn't\\\": 24, \\\"lions\\\": 64, \\\"am\\\": 24, \\\"mice\\\": 64, \\\"have\\\": 12}\", \"index_docs\": \"{\\\"44\\\": 8954, \\\"8\\\": 32946, \\\"17\\\": 12197, \\\"39\\\": 9004, \\\"3\\\": 75137, \\\"55\\\": 8898, \\\"7\\\": 59850, \\\"2\\\": 75525, \\\"67\\\": 8693, \\\"1\\\": 104561, \\\"23\\\": 11225, \\\"4\\\": 74933, \\\"20\\\": 11270, \\\"21\\\": 11270, \\\"62\\\": 8770, \\\"51\\\": 8928, \\\"9\\\": 32846, \\\"45\\\": 8951, \\\"5\\\": 41221, \\\"43\\\": 8956, \\\"38\\\": 9023, \\\"34\\\": 9133, \\\"22\\\": 11250, \\\"68\\\": 8639, \\\"42\\\": 8958, \\\"64\\\": 8743, \\\"57\\\": 8878, \\\"16\\\": 7446, \\\"82\\\": 4848, \\\"6\\\": 63987, \\\"12\\\": 14364, \\\"83\\\": 4848, \\\"30\\\": 9700, \\\"29\\\": 9734, \\\"13\\\": 27192, \\\"31\\\": 9700, \\\"11\\\": 15132, \\\"84\\\": 4848, \\\"47\\\": 8945, \\\"66\\\": 8696, \\\"18\\\": 11334, \\\"35\\\": 9102, \\\"10\\\": 32834, \\\"60\\\": 8791, \\\"49\\\": 8932, \\\"85\\\": 4848, \\\"56\\\": 8890, \\\"36\\\": 9090, \\\"86\\\": 4848, \\\"32\\\": 9700, \\\"87\\\": 4848, \\\"111\\\": 972, \\\"101\\\": 1944, \\\"100\\\": 1944, \\\"127\\\": 648, \\\"26\\\": 10786, \\\"112\\\": 972, \\\"19\\\": 11277, \\\"63\\\": 8761, \\\"14\\\": 8334, \\\"99\\\": 2304, \\\"104\\\": 1867, \\\"153\\\": 192, \\\"95\\\": 2712, \\\"15\\\": 7566, \\\"28\\\": 10692, \\\"71\\\": 5844, \\\"69\\\": 7314, \\\"72\\\": 5844, \\\"48\\\": 8942, \\\"52\\\": 8916, \\\"54\\\": 8910, \\\"25\\\": 10953, \\\"58\\\": 8808, \\\"41\\\": 8984, \\\"46\\\": 8948, \\\"24\\\": 11170, \\\"40\\\": 8995, \\\"74\\\": 5844, \\\"73\\\": 5844, \\\"88\\\": 4848, \\\"89\\\": 4848, \\\"50\\\": 8932, \\\"61\\\": 8789, \\\"53\\\": 8915, \\\"75\\\": 5844, \\\"76\\\": 5844, \\\"122\\\": 768, \\\"154\\\": 192, \\\"59\\\": 8794, \\\"65\\\": 8726, \\\"97\\\": 2532, \\\"92\\\": 4588, \\\"77\\\": 5844, \\\"94\\\": 3222, \\\"78\\\": 5844, \\\"113\\\": 972, \\\"109\\\": 1016, \\\"27\\\": 10786, \\\"37\\\": 9038, \\\"114\\\": 972, \\\"128\\\": 648, \\\"102\\\": 1944, \\\"79\\\": 5844, \\\"96\\\": 2664, \\\"90\\\": 4848, \\\"80\\\": 5844, \\\"81\\\": 4170, \\\"126\\\": 666, \\\"105\\\": 1666, \\\"108\\\": 1224, \\\"125\\\": 714, \\\"123\\\": 768, \\\"134\\\": 384, \\\"169\\\": 64, \\\"120\\\": 870, \\\"70\\\": 7314, \\\"93\\\": 4444, \\\"33\\\": 9134, \\\"107\\\": 1296, \\\"91\\\": 4848, \\\"129\\\": 648, \\\"115\\\": 972, \\\"98\\\": 2414, \\\"155\\\": 192, \\\"170\\\": 64, \\\"156\\\": 192, \\\"135\\\": 378, \\\"121\\\": 781, \\\"157\\\": 192, \\\"103\\\": 1944, \\\"171\\\": 64, \\\"116\\\": 972, \\\"158\\\": 192, \\\"117\\\": 972, \\\"132\\\": 480, \\\"149\\\": 240, \\\"140\\\": 312, \\\"145\\\": 260, \\\"139\\\": 312, \\\"131\\\": 540, \\\"110\\\": 1016, \\\"118\\\": 972, \\\"146\\\": 260, \\\"144\\\": 300, \\\"198\\\": 12, \\\"159\\\": 192, \\\"150\\\": 240, \\\"106\\\": 1386, \\\"136\\\": 378, \\\"124\\\": 768, \\\"130\\\": 648, \\\"119\\\": 972, \\\"172\\\": 64, \\\"160\\\": 192, \\\"193\\\": 33, \\\"168\\\": 67, \\\"161\\\": 192, \\\"133\\\": 476, \\\"162\\\": 192, \\\"163\\\": 192, \\\"141\\\": 312, \\\"151\\\": 240, \\\"183\\\": 57, \\\"165\\\": 144, \\\"182\\\": 57, \\\"184\\\": 57, \\\"152\\\": 204, \\\"185\\\": 57, \\\"137\\\": 378, \\\"186\\\": 57, \\\"187\\\": 57, \\\"194\\\": 24, \\\"148\\\": 252, \\\"181\\\": 60, \\\"164\\\": 192, \\\"173\\\": 64, \\\"147\\\": 260, \\\"167\\\": 84, \\\"143\\\": 312, \\\"138\\\": 360, \\\"142\\\": 312, \\\"190\\\": 48, \\\"191\\\": 36, \\\"174\\\": 64, \\\"175\\\": 64, \\\"195\\\": 24, \\\"192\\\": 36, \\\"176\\\": 64, \\\"188\\\": 57, \\\"177\\\": 64, \\\"189\\\": 57, \\\"178\\\": 64, \\\"166\\\": 126, \\\"196\\\": 24, \\\"179\\\": 64, \\\"197\\\": 24, \\\"180\\\": 64, \\\"199\\\": 12}\", \"index_word\": \"{\\\"1\\\": \\\"is\\\", \\\"2\\\": \\\"in\\\", \\\"3\\\": \\\"it\\\", \\\"4\\\": \\\"during\\\", \\\"5\\\": \\\"the\\\", \\\"6\\\": \\\"but\\\", \\\"7\\\": \\\"and\\\", \\\"8\\\": \\\"sometimes\\\", \\\"9\\\": \\\"usually\\\", \\\"10\\\": \\\"never\\\", \\\"11\\\": \\\"favorite\\\", \\\"12\\\": \\\"least\\\", \\\"13\\\": \\\"fruit\\\", \\\"14\\\": \\\"most\\\", \\\"15\\\": \\\"loved\\\", \\\"16\\\": \\\"liked\\\", \\\"17\\\": \\\"new\\\", \\\"18\\\": \\\"paris\\\", \\\"19\\\": \\\"india\\\", \\\"20\\\": \\\"united\\\", \\\"21\\\": \\\"states\\\", \\\"22\\\": \\\"california\\\", \\\"23\\\": \\\"jersey\\\", \\\"24\\\": \\\"france\\\", \\\"25\\\": \\\"china\\\", \\\"26\\\": \\\"he\\\", \\\"27\\\": \\\"she\\\", \\\"28\\\": \\\"grapefruit\\\", \\\"29\\\": \\\"your\\\", \\\"30\\\": \\\"my\\\", \\\"31\\\": \\\"his\\\", \\\"32\\\": \\\"her\\\", \\\"33\\\": \\\"fall\\\", \\\"34\\\": \\\"june\\\", \\\"35\\\": \\\"spring\\\", \\\"36\\\": \\\"january\\\", \\\"37\\\": \\\"winter\\\", \\\"38\\\": \\\"march\\\", \\\"39\\\": \\\"autumn\\\", \\\"40\\\": \\\"may\\\", \\\"41\\\": \\\"nice\\\", \\\"42\\\": \\\"september\\\", \\\"43\\\": \\\"july\\\", \\\"44\\\": \\\"april\\\", \\\"45\\\": \\\"november\\\", \\\"46\\\": \\\"summer\\\", \\\"47\\\": \\\"december\\\", \\\"48\\\": \\\"february\\\", \\\"49\\\": \\\"our\\\", \\\"50\\\": \\\"their\\\", \\\"51\\\": \\\"freezing\\\", \\\"52\\\": \\\"pleasant\\\", \\\"53\\\": \\\"beautiful\\\", \\\"54\\\": \\\"october\\\", \\\"55\\\": \\\"snowy\\\", \\\"56\\\": \\\"warm\\\", \\\"57\\\": \\\"cold\\\", \\\"58\\\": \\\"wonderful\\\", \\\"59\\\": \\\"dry\\\", \\\"60\\\": \\\"busy\\\", \\\"61\\\": \\\"august\\\", \\\"62\\\": \\\"chilly\\\", \\\"63\\\": \\\"rainy\\\", \\\"64\\\": \\\"mild\\\", \\\"65\\\": \\\"wet\\\", \\\"66\\\": \\\"relaxing\\\", \\\"67\\\": \\\"quiet\\\", \\\"68\\\": \\\"hot\\\", \\\"69\\\": \\\"dislikes\\\", \\\"70\\\": \\\"likes\\\", \\\"71\\\": \\\"limes\\\", \\\"72\\\": \\\"lemons\\\", \\\"73\\\": \\\"grapes\\\", \\\"74\\\": \\\"mangoes\\\", \\\"75\\\": \\\"apples\\\", \\\"76\\\": \\\"peaches\\\", \\\"77\\\": \\\"oranges\\\", \\\"78\\\": \\\"pears\\\", \\\"79\\\": \\\"strawberries\\\", \\\"80\\\": \\\"bananas\\\", \\\"81\\\": \\\"to\\\", \\\"82\\\": \\\"grape\\\", \\\"83\\\": \\\"apple\\\", \\\"84\\\": \\\"orange\\\", \\\"85\\\": \\\"lemon\\\", \\\"86\\\": \\\"lime\\\", \\\"87\\\": \\\"banana\\\", \\\"88\\\": \\\"mango\\\", \\\"89\\\": \\\"pear\\\", \\\"90\\\": \\\"strawberry\\\", \\\"91\\\": \\\"peach\\\", \\\"92\\\": \\\"like\\\", \\\"93\\\": \\\"dislike\\\", \\\"94\\\": \\\"they\\\", \\\"95\\\": \\\"that\\\", \\\"96\\\": \\\"i\\\", \\\"97\\\": \\\"we\\\", \\\"98\\\": \\\"you\\\", \\\"99\\\": \\\"animal\\\", \\\"100\\\": \\\"a\\\", \\\"101\\\": \\\"truck\\\", \\\"102\\\": \\\"car\\\", \\\"103\\\": \\\"automobile\\\", \\\"104\\\": \\\"was\\\", \\\"105\\\": \\\"next\\\", \\\"106\\\": \\\"go\\\", \\\"107\\\": \\\"driving\\\", \\\"108\\\": \\\"visit\\\", \\\"109\\\": \\\"little\\\", \\\"110\\\": \\\"big\\\", \\\"111\\\": \\\"old\\\", \\\"112\\\": \\\"yellow\\\", \\\"113\\\": \\\"red\\\", \\\"114\\\": \\\"rusty\\\", \\\"115\\\": \\\"blue\\\", \\\"116\\\": \\\"white\\\", \\\"117\\\": \\\"black\\\", \\\"118\\\": \\\"green\\\", \\\"119\\\": \\\"shiny\\\", \\\"120\\\": \\\"are\\\", \\\"121\\\": \\\"last\\\", \\\"122\\\": \\\"feared\\\", \\\"123\\\": \\\"animals\\\", \\\"124\\\": \\\"this\\\", \\\"125\\\": \\\"plan\\\", \\\"126\\\": \\\"going\\\", \\\"127\\\": \\\"saw\\\", \\\"128\\\": \\\"disliked\\\", \\\"129\\\": \\\"drives\\\", \\\"130\\\": \\\"drove\\\", \\\"131\\\": \\\"between\\\", \\\"132\\\": \\\"translate\\\", \\\"133\\\": \\\"plans\\\", \\\"134\\\": \\\"were\\\", \\\"135\\\": \\\"went\\\", \\\"136\\\": \\\"might\\\", \\\"137\\\": \\\"wanted\\\", \\\"138\\\": \\\"thinks\\\", \\\"139\\\": \\\"spanish\\\", \\\"140\\\": \\\"portuguese\\\", \\\"141\\\": \\\"chinese\\\", \\\"142\\\": \\\"english\\\", \\\"143\\\": \\\"french\\\", \\\"144\\\": \\\"translating\\\", \\\"145\\\": \\\"difficult\\\", \\\"146\\\": \\\"fun\\\", \\\"147\\\": \\\"easy\\\", \\\"148\\\": \\\"wants\\\", \\\"149\\\": \\\"think\\\", \\\"150\\\": \\\"why\\\", \\\"151\\\": \\\"it's\\\", \\\"152\\\": \\\"did\\\", \\\"153\\\": \\\"cat\\\", \\\"154\\\": \\\"shark\\\", \\\"155\\\": \\\"bird\\\", \\\"156\\\": \\\"mouse\\\", \\\"157\\\": \\\"horse\\\", \\\"158\\\": \\\"elephant\\\", \\\"159\\\": \\\"dog\\\", \\\"160\\\": \\\"monkey\\\", \\\"161\\\": \\\"lion\\\", \\\"162\\\": \\\"bear\\\", \\\"163\\\": \\\"rabbit\\\", \\\"164\\\": \\\"snake\\\", \\\"165\\\": \\\"when\\\", \\\"166\\\": \\\"want\\\", \\\"167\\\": \\\"do\\\", \\\"168\\\": \\\"how\\\", \\\"169\\\": \\\"elephants\\\", \\\"170\\\": \\\"horses\\\", \\\"171\\\": \\\"dogs\\\", \\\"172\\\": \\\"sharks\\\", \\\"173\\\": \\\"snakes\\\", \\\"174\\\": \\\"cats\\\", \\\"175\\\": \\\"rabbits\\\", \\\"176\\\": \\\"monkeys\\\", \\\"177\\\": \\\"bears\\\", \\\"178\\\": \\\"birds\\\", \\\"179\\\": \\\"lions\\\", \\\"180\\\": \\\"mice\\\", \\\"181\\\": \\\"didn't\\\", \\\"182\\\": \\\"eiffel\\\", \\\"183\\\": \\\"tower\\\", \\\"184\\\": \\\"grocery\\\", \\\"185\\\": \\\"store\\\", \\\"186\\\": \\\"football\\\", \\\"187\\\": \\\"field\\\", \\\"188\\\": \\\"lake\\\", \\\"189\\\": \\\"school\\\", \\\"190\\\": \\\"would\\\", \\\"191\\\": \\\"aren't\\\", \\\"192\\\": \\\"been\\\", \\\"193\\\": \\\"weather\\\", \\\"194\\\": \\\"does\\\", \\\"195\\\": \\\"has\\\", \\\"196\\\": \\\"isn't\\\", \\\"197\\\": \\\"am\\\", \\\"198\\\": \\\"where\\\", \\\"199\\\": \\\"have\\\"}\", \"word_index\": \"{\\\"is\\\": 1, \\\"in\\\": 2, \\\"it\\\": 3, \\\"during\\\": 4, \\\"the\\\": 5, \\\"but\\\": 6, \\\"and\\\": 7, \\\"sometimes\\\": 8, \\\"usually\\\": 9, \\\"never\\\": 10, \\\"favorite\\\": 11, \\\"least\\\": 12, \\\"fruit\\\": 13, \\\"most\\\": 14, \\\"loved\\\": 15, \\\"liked\\\": 16, \\\"new\\\": 17, \\\"paris\\\": 18, \\\"india\\\": 19, \\\"united\\\": 20, \\\"states\\\": 21, \\\"california\\\": 22, \\\"jersey\\\": 23, \\\"france\\\": 24, \\\"china\\\": 25, \\\"he\\\": 26, \\\"she\\\": 27, \\\"grapefruit\\\": 28, \\\"your\\\": 29, \\\"my\\\": 30, \\\"his\\\": 31, \\\"her\\\": 32, \\\"fall\\\": 33, \\\"june\\\": 34, \\\"spring\\\": 35, \\\"january\\\": 36, \\\"winter\\\": 37, \\\"march\\\": 38, \\\"autumn\\\": 39, \\\"may\\\": 40, \\\"nice\\\": 41, \\\"september\\\": 42, \\\"july\\\": 43, \\\"april\\\": 44, \\\"november\\\": 45, \\\"summer\\\": 46, \\\"december\\\": 47, \\\"february\\\": 48, \\\"our\\\": 49, \\\"their\\\": 50, \\\"freezing\\\": 51, \\\"pleasant\\\": 52, \\\"beautiful\\\": 53, \\\"october\\\": 54, \\\"snowy\\\": 55, \\\"warm\\\": 56, \\\"cold\\\": 57, \\\"wonderful\\\": 58, \\\"dry\\\": 59, \\\"busy\\\": 60, \\\"august\\\": 61, \\\"chilly\\\": 62, \\\"rainy\\\": 63, \\\"mild\\\": 64, \\\"wet\\\": 65, \\\"relaxing\\\": 66, \\\"quiet\\\": 67, \\\"hot\\\": 68, \\\"dislikes\\\": 69, \\\"likes\\\": 70, \\\"limes\\\": 71, \\\"lemons\\\": 72, \\\"grapes\\\": 73, \\\"mangoes\\\": 74, \\\"apples\\\": 75, \\\"peaches\\\": 76, \\\"oranges\\\": 77, \\\"pears\\\": 78, \\\"strawberries\\\": 79, \\\"bananas\\\": 80, \\\"to\\\": 81, \\\"grape\\\": 82, \\\"apple\\\": 83, \\\"orange\\\": 84, \\\"lemon\\\": 85, \\\"lime\\\": 86, \\\"banana\\\": 87, \\\"mango\\\": 88, \\\"pear\\\": 89, \\\"strawberry\\\": 90, \\\"peach\\\": 91, \\\"like\\\": 92, \\\"dislike\\\": 93, \\\"they\\\": 94, \\\"that\\\": 95, \\\"i\\\": 96, \\\"we\\\": 97, \\\"you\\\": 98, \\\"animal\\\": 99, \\\"a\\\": 100, \\\"truck\\\": 101, \\\"car\\\": 102, \\\"automobile\\\": 103, \\\"was\\\": 104, \\\"next\\\": 105, \\\"go\\\": 106, \\\"driving\\\": 107, \\\"visit\\\": 108, \\\"little\\\": 109, \\\"big\\\": 110, \\\"old\\\": 111, \\\"yellow\\\": 112, \\\"red\\\": 113, \\\"rusty\\\": 114, \\\"blue\\\": 115, \\\"white\\\": 116, \\\"black\\\": 117, \\\"green\\\": 118, \\\"shiny\\\": 119, \\\"are\\\": 120, \\\"last\\\": 121, \\\"feared\\\": 122, \\\"animals\\\": 123, \\\"this\\\": 124, \\\"plan\\\": 125, \\\"going\\\": 126, \\\"saw\\\": 127, \\\"disliked\\\": 128, \\\"drives\\\": 129, \\\"drove\\\": 130, \\\"between\\\": 131, \\\"translate\\\": 132, \\\"plans\\\": 133, \\\"were\\\": 134, \\\"went\\\": 135, \\\"might\\\": 136, \\\"wanted\\\": 137, \\\"thinks\\\": 138, \\\"spanish\\\": 139, \\\"portuguese\\\": 140, \\\"chinese\\\": 141, \\\"english\\\": 142, \\\"french\\\": 143, \\\"translating\\\": 144, \\\"difficult\\\": 145, \\\"fun\\\": 146, \\\"easy\\\": 147, \\\"wants\\\": 148, \\\"think\\\": 149, \\\"why\\\": 150, \\\"it's\\\": 151, \\\"did\\\": 152, \\\"cat\\\": 153, \\\"shark\\\": 154, \\\"bird\\\": 155, \\\"mouse\\\": 156, \\\"horse\\\": 157, \\\"elephant\\\": 158, \\\"dog\\\": 159, \\\"monkey\\\": 160, \\\"lion\\\": 161, \\\"bear\\\": 162, \\\"rabbit\\\": 163, \\\"snake\\\": 164, \\\"when\\\": 165, \\\"want\\\": 166, \\\"do\\\": 167, \\\"how\\\": 168, \\\"elephants\\\": 169, \\\"horses\\\": 170, \\\"dogs\\\": 171, \\\"sharks\\\": 172, \\\"snakes\\\": 173, \\\"cats\\\": 174, \\\"rabbits\\\": 175, \\\"monkeys\\\": 176, \\\"bears\\\": 177, \\\"birds\\\": 178, \\\"lions\\\": 179, \\\"mice\\\": 180, \\\"didn't\\\": 181, \\\"eiffel\\\": 182, \\\"tower\\\": 183, \\\"grocery\\\": 184, \\\"store\\\": 185, \\\"football\\\": 186, \\\"field\\\": 187, \\\"lake\\\": 188, \\\"school\\\": 189, \\\"would\\\": 190, \\\"aren't\\\": 191, \\\"been\\\": 192, \\\"weather\\\": 193, \\\"does\\\": 194, \\\"has\\\": 195, \\\"isn't\\\": 196, \\\"am\\\": 197, \\\"where\\\": 198, \\\"have\\\": 199}\"}}"

Task 2/french_tokenizer.json

@@ -0,0 +1 @@
+"{\"class_name\": \"Tokenizer\", \"config\": {\"num_words\": null, \"filters\": \"!\\\"#$%&()*+,-./:;<=>?@[\\\\]^_`{|}~\\t\\n\", \"lower\": true, \"split\": \" \", \"char_level\": false, \"oov_token\": null, \"document_count\": 137861, \"word_counts\": \"{\\\"new\\\": 11047, \\\"jersey\\\": 11052, \\\"est\\\": 196821, \\\"parfois\\\": 37746, \\\"calme\\\": 7256, \\\"pendant\\\": 10741, \\\"l'\\\": 32917, \\\"automne\\\": 14727, \\\"et\\\": 59851, \\\"il\\\": 84115, \\\"neigeux\\\": 1867, \\\"en\\\": 105768, \\\"avril\\\": 8954, \\\"les\\\": 65255, \\\"\\\\u00e9tats\\\": 11267, \\\"unis\\\": 11270, \\\"g\\\\u00e9n\\\\u00e9ralement\\\": 31292, \\\"froid\\\": 16794, \\\"juillet\\\": 8956, \\\"g\\\\u00e8le\\\": 3622, \\\"habituellement\\\": 6215, \\\"novembre\\\": 8951, \\\"california\\\": 3061, \\\"mars\\\": 9023, \\\"chaud\\\": 16405, \\\"juin\\\": 9133, \\\"l\\\\u00e9g\\\\u00e8re\\\": 63, \\\"fait\\\": 2916, \\\"septembre\\\": 8958, \\\"votre\\\": 9368, \\\"moins\\\": 27557, \\\"aim\\\\u00e9\\\": 25852, \\\"fruit\\\": 23626, \\\"le\\\": 35306, \\\"raisin\\\": 4852, \\\"mais\\\": 63987, \\\"mon\\\": 9403, \\\"la\\\": 49861, \\\"pomme\\\": 4848, \\\"son\\\": 16496, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9\\\": 23305, \\\"l'orange\\\": 4848, \\\"paris\\\": 11334, \\\"relaxant\\\": 8458, \\\"d\\\\u00e9cembre\\\": 8945, \\\"occup\\\\u00e9\\\": 7782, \\\"au\\\": 25738, \\\"printemps\\\": 9100, \\\"jamais\\\": 37215, \\\"chaude\\\": 1124, \\\"notre\\\": 8319, \\\"citron\\\": 4848, \\\"janvier\\\": 9090, \\\"chaux\\\": 4848, \\\"des\\\": 2435, \\\"fruits\\\": 3566, \\\"banane\\\": 4848, \\\"a\\\": 1356, \\\"vu\\\": 645, \\\"un\\\": 698, \\\"vieux\\\": 325, \\\"camion\\\": 1944, \\\"jaune\\\": 972, \\\"inde\\\": 11277, \\\"pluvieux\\\": 7658, \\\"ce\\\": 1572, \\\"chat\\\": 192, \\\"\\\\u00e9tait\\\": 1198, \\\"animal\\\": 2248, \\\"plus\\\": 14934, \\\"n'aime\\\": 3131, \\\"pamplemousse\\\": 10140, \\\"citrons\\\": 11679, \\\"verts\\\": 5835, \\\"californie\\\": 8189, \\\"ne\\\": 2715, \\\"f\\\\u00e9vrier\\\": 8942, \\\"gel\\\": 4886, \\\"chine\\\": 10936, \\\"agr\\\\u00e9able\\\": 17751, \\\"octobre\\\": 8911, \\\"merveilleux\\\": 8704, \\\"doux\\\": 8458, \\\"tranquille\\\": 1437, \\\"\\\\u00e0\\\": 13870, \\\"l'automne\\\": 3411, \\\"\\\\u00e9t\\\\u00e9\\\": 8999, \\\"france\\\": 11170, \\\"mois\\\": 14350, \\\"de\\\": 15070, \\\"mai\\\": 8995, \\\"frisquet\\\": 834, \\\"d\\\\u00e9teste\\\": 3743, \\\"raisins\\\": 5780, \\\"mangues\\\": 5774, \\\"leur\\\": 7855, \\\"mangue\\\": 4899, \\\"poire\\\": 4848, \\\"ao\\\\u00fbt\\\": 8789, \\\"beau\\\": 6387, \\\"pommes\\\": 5844, \\\"p\\\\u00eaches\\\": 5844, \\\"redout\\\\u00e9\\\": 576, \\\"que\\\": 667, \\\"requin\\\": 192, \\\"humide\\\": 8446, \\\"d'\\\": 5100, \\\"sec\\\": 7957, \\\"enneig\\\\u00e9e\\\": 4008, \\\"nous\\\": 2520, \\\"aimons\\\": 1111, \\\"oranges\\\": 5844, \\\"ils\\\": 3221, \\\"aiment\\\": 1126, \\\"poires\\\": 5844, \\\"elle\\\": 12080, \\\"petit\\\": 324, \\\"rouge\\\": 972, \\\"cher\\\": 1308, \\\"aim\\\\u00e9e\\\": 105, \\\"neige\\\": 3016, \\\"trop\\\": 173, \\\"monde\\\": 173, \\\"hiver\\\": 9038, \\\"sont\\\": 1018, \\\"n'aimait\\\": 561, \\\"pas\\\": 4495, \\\"une\\\": 1278, \\\"voiture\\\": 3510, \\\"rouill\\\\u00e9e\\\": 486, \\\"fraises\\\": 5844, \\\"cours\\\": 1927, \\\"j'aime\\\": 966, \\\"fraise\\\": 4848, \\\"bananes\\\": 5844, \\\"va\\\": 355, \\\"aux\\\": 392, \\\"prochain\\\": 1666, \\\"je\\\": 1548, \\\"pr\\\\u00e9vois\\\": 233, \\\"visiter\\\": 908, \\\"belle\\\": 2726, \\\"\\\\u00e9l\\\\u00e9phants\\\": 64, \\\"\\\\u00e9taient\\\": 357, \\\"ses\\\": 402, \\\"animaux\\\": 768, \\\"redout\\\\u00e9s\\\": 190, \\\"vont\\\": 168, \\\"aime\\\": 8870, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9e\\\": 770, \\\"n'aiment\\\": 1111, \\\"i\\\": 150, \\\"comme\\\": 259, \\\"conduit\\\": 1706, \\\"p\\\\u00eache\\\": 4848, \\\"nouvelle\\\": 648, \\\"bleue\\\": 504, \\\"vous\\\": 2541, \\\"aimez\\\": 1053, \\\"cet\\\": 286, \\\"oiseau\\\": 128, \\\"pamplemousses\\\": 552, \\\"pleut\\\": 562, \\\"magnifique\\\": 104, \\\"favori\\\": 3857, \\\"vos\\\": 225, \\\"aim\\\\u00e9s\\\": 237, \\\"chevaux\\\": 64, \\\"n'aimez\\\": 1094, \\\"n'aimons\\\": 97, \\\"souris\\\": 256, \\\"d\\\\u00e9testons\\\": 1001, \\\"all\\\\u00e9\\\": 187, \\\"dernier\\\": 757, \\\"conduisait\\\": 673, \\\"petite\\\": 615, \\\"glaciales\\\": 307, \\\"cheval\\\": 192, \\\"vieille\\\": 647, \\\"chiens\\\": 64, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9s\\\": 383, \\\"blanche\\\": 579, \\\"occup\\\\u00e9e\\\": 836, \\\"nos\\\": 613, \\\"l'\\\\u00e9l\\\\u00e9phant\\\": 64, \\\"nouveau\\\": 502, \\\"noire\\\": 602, \\\"pluies\\\": 367, \\\"pense\\\": 540, \\\"qu'il\\\": 393, \\\"difficile\\\": 260, \\\"traduire\\\": 501, \\\"entre\\\": 540, \\\"espagnol\\\": 312, \\\"portugais\\\": 312, \\\"bleu\\\": 468, \\\"rouill\\\\u00e9\\\": 454, \\\"aimait\\\": 707, \\\"grande\\\": 459, \\\"verte\\\": 628, \\\"traduction\\\": 277, \\\"amusant\\\": 260, \\\"cette\\\": 1239, \\\"vert\\\": 344, \\\"grand\\\": 81, \\\"blanc\\\": 393, \\\"volant\\\": 165, \\\"gros\\\": 258, \\\"o\\\\u00f9\\\": 12, \\\"chien\\\": 192, \\\"leurs\\\": 1072, \\\"pourquoi\\\": 240, \\\"l'automobile\\\": 100, \\\"pourrait\\\": 252, \\\"se\\\": 461, \\\"rendre\\\": 350, \\\"pr\\\\u00e9voyons\\\": 232, \\\"maillot\\\": 173, \\\"grosse\\\": 185, \\\"brillant\\\": 587, \\\"pr\\\\u00e9voient\\\": 75, \\\"mouill\\\\u00e9e\\\": 7, \\\"lui\\\": 70, \\\"d\\\\u00e9tendre\\\": 111, \\\"automobile\\\": 278, \\\"pourraient\\\": 126, \\\"aller\\\": 1180, \\\"mes\\\": 297, \\\"s\\\\u00e8che\\\": 837, \\\"l'oiseau\\\": 64, \\\"pluie\\\": 174, \\\"requins\\\": 64, \\\"noir\\\": 370, \\\"singe\\\": 192, \\\"d\\\\u00e9testait\\\": 87, \\\"comment\\\": 67, \\\"temps\\\": 33, \\\"dans\\\": 12, \\\"lion\\\": 192, \\\"pr\\\\u00e9voit\\\": 75, \\\"ours\\\": 192, \\\"porcelaine\\\": 17, \\\"cl\\\\u00e9mentes\\\": 200, \\\"pla\\\\u00eet\\\": 13, \\\"proches\\\": 20, \\\"brillante\\\": 385, \\\"lapin\\\": 192, \\\"l'ours\\\": 64, \\\"chinois\\\": 312, \\\"quand\\\": 144, \\\"tour\\\": 57, \\\"eiffel\\\": 57, \\\"allons\\\": 45, \\\"l'\\\\u00e9picerie\\\": 57, \\\"voulait\\\": 252, \\\"c\\\\u00e9page\\\": 60, \\\"t\\\": 18, \\\"terrain\\\": 57, \\\"football\\\": 57, \\\"du\\\": 39, \\\"veut\\\": 252, \\\"\\\\u00e9l\\\\u00e9phant\\\": 128, \\\"gel\\\\u00e9\\\": 94, \\\"bien\\\": 77, \\\"enneig\\\\u00e9\\\": 7, \\\"gel\\\\u00e9s\\\": 5, \\\"serpent\\\": 192, \\\"all\\\\u00e9s\\\": 150, \\\"all\\\\u00e9e\\\": 150, \\\"envisage\\\": 360, \\\"peu\\\": 41, \\\"mouill\\\\u00e9\\\": 273, \\\"serpents\\\": 64, \\\"pensez\\\": 60, \\\"facile\\\": 260, \\\"anglais\\\": 312, \\\"fran\\\\u00e7ais\\\": 312, \\\"voulez\\\": 12, \\\"grandes\\\": 16, \\\"avez\\\": 162, \\\"aimeraient\\\": 12, \\\"allez\\\": 45, \\\"chats\\\": 64, \\\"lapins\\\": 64, \\\"visite\\\": 68, \\\"ont\\\": 194, \\\"intention\\\": 206, \\\"n'est\\\": 47, \\\"derni\\\\u00e8re\\\": 24, \\\"voulaient\\\": 126, \\\"singes\\\": 64, \\\"\\\\u00eates\\\": 24, \\\"qu'elle\\\": 26, \\\"vers\\\": 76, \\\"lac\\\": 57, \\\"pousse\\\": 41, \\\"d\\\\u00e9testez\\\": 17, \\\"manguiers\\\": 19, \\\"grands\\\": 9, \\\"l'\\\\u00e9cole\\\": 57, \\\"l'animal\\\": 56, \\\"at\\\": 32, \\\"oiseaux\\\": 64, \\\"ressort\\\": 2, \\\"petits\\\": 10, \\\"n'a\\\": 12, \\\"veulent\\\": 126, \\\"rouille\\\": 32, \\\"frais\\\": 20, \\\"limes\\\": 9, \\\"lions\\\": 64, \\\"douce\\\": 14, \\\"envisagent\\\": 9, \\\"petites\\\": 26, \\\"vais\\\": 24, \\\"durant\\\": 14, \\\"c'est\\\": 17, \\\"cong\\\\u00e9lation\\\": 14, \\\"allions\\\": 1, \\\"voudrait\\\": 24, \\\"d\\\\u00e9tend\\\": 2, \\\"trouv\\\\u00e9\\\": 1, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9es\\\": 16, \\\"conduite\\\": 6, \\\"grosses\\\": 8, \\\"b\\\\u00e9nigne\\\": 8, \\\"avons\\\": 19, \\\"sur\\\": 28, \\\"redout\\\\u00e9e\\\": 2, \\\"etats\\\": 3, \\\"moindres\\\": 7, \\\"n'\\\\u00eates\\\": 3, \\\"vit\\\": 3, \\\"as\\\": 1, \\\"tu\\\": 2, \\\"qui\\\": 2, \\\"faire\\\": 1, \\\"traduis\\\": 2, \\\"favoris\\\": 1, \\\"souvent\\\": 1, \\\"es\\\": 1, \\\"appr\\\\u00e9ci\\\\u00e9\\\": 2, \\\"moteur\\\": 1, \\\"tout\\\": 4}\", \"word_docs\": \"{\\\"l'\\\": 28828, \\\"en\\\": 72048, \\\"automne\\\": 14398, \\\"calme\\\": 7256, \\\"et\\\": 59851, \\\"neigeux\\\": 1867, \\\"est\\\": 104279, \\\"il\\\": 84114, \\\"pendant\\\": 10741, \\\"new\\\": 11047, \\\"parfois\\\": 32946, \\\"jersey\\\": 11052, \\\"avril\\\": 8954, \\\"unis\\\": 11270, \\\"froid\\\": 16323, \\\"les\\\": 33404, \\\"juillet\\\": 8956, \\\"\\\\u00e9tats\\\": 11267, \\\"habituellement\\\": 6112, \\\"g\\\\u00e8le\\\": 3622, \\\"novembre\\\": 8951, \\\"g\\\\u00e9n\\\\u00e9ralement\\\": 28101, \\\"mars\\\": 9023, \\\"chaud\\\": 15908, \\\"california\\\": 3061, \\\"juin\\\": 9133, \\\"l\\\\u00e9g\\\\u00e8re\\\": 63, \\\"fait\\\": 2916, \\\"septembre\\\": 8958, \\\"mon\\\": 9403, \\\"moins\\\": 14357, \\\"votre\\\": 9368, \\\"mais\\\": 63987, \\\"la\\\": 39038, \\\"raisin\\\": 4852, \\\"fruit\\\": 23626, \\\"aim\\\\u00e9\\\": 14038, \\\"pomme\\\": 4848, \\\"le\\\": 28877, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9\\\": 14722, \\\"l'orange\\\": 4848, \\\"son\\\": 15184, \\\"relaxant\\\": 8458, \\\"paris\\\": 11334, \\\"d\\\\u00e9cembre\\\": 8945, \\\"printemps\\\": 9100, \\\"occup\\\\u00e9\\\": 7782, \\\"au\\\": 24675, \\\"jamais\\\": 32618, \\\"chaude\\\": 1124, \\\"citron\\\": 4848, \\\"notre\\\": 8319, \\\"janvier\\\": 9090, \\\"banane\\\": 4848, \\\"fruits\\\": 3566, \\\"chaux\\\": 4848, \\\"des\\\": 2435, \\\"a\\\": 1356, \\\"jaune\\\": 972, \\\"vu\\\": 645, \\\"camion\\\": 1944, \\\"vieux\\\": 325, \\\"un\\\": 698, \\\"inde\\\": 11277, \\\"pluvieux\\\": 7658, \\\"animal\\\": 2248, \\\"\\\\u00e9tait\\\": 1198, \\\"plus\\\": 8334, \\\"chat\\\": 192, \\\"ce\\\": 1572, \\\"pamplemousse\\\": 10140, \\\"n'aime\\\": 3131, \\\"verts\\\": 5835, \\\"citrons\\\": 10568, \\\"gel\\\": 4886, \\\"f\\\\u00e9vrier\\\": 8942, \\\"californie\\\": 8189, \\\"ne\\\": 2707, \\\"chine\\\": 10936, \\\"agr\\\\u00e9able\\\": 17151, \\\"octobre\\\": 8910, \\\"merveilleux\\\": 8704, \\\"doux\\\": 8458, \\\"tranquille\\\": 1437, \\\"\\\\u00e0\\\": 13381, \\\"l'automne\\\": 3411, \\\"\\\\u00e9t\\\\u00e9\\\": 8999, \\\"france\\\": 11170, \\\"mois\\\": 14311, \\\"mai\\\": 8995, \\\"frisquet\\\": 834, \\\"de\\\": 14740, \\\"mangues\\\": 5774, \\\"d\\\\u00e9teste\\\": 3743, \\\"raisins\\\": 5780, \\\"mangue\\\": 4899, \\\"poire\\\": 4848, \\\"leur\\\": 7855, \\\"ao\\\\u00fbt\\\": 8789, \\\"beau\\\": 6387, \\\"pommes\\\": 5844, \\\"p\\\\u00eaches\\\": 5844, \\\"requin\\\": 192, \\\"redout\\\\u00e9\\\": 576, \\\"que\\\": 667, \\\"d'\\\": 5100, \\\"sec\\\": 7957, \\\"humide\\\": 8446, \\\"enneig\\\\u00e9e\\\": 4008, \\\"aimons\\\": 1111, \\\"nous\\\": 2520, \\\"oranges\\\": 5844, \\\"poires\\\": 5844, \\\"ils\\\": 3221, \\\"aiment\\\": 1126, \\\"petit\\\": 324, \\\"rouge\\\": 972, \\\"elle\\\": 12080, \\\"aim\\\\u00e9e\\\": 105, \\\"cher\\\": 1308, \\\"monde\\\": 173, \\\"neige\\\": 3016, \\\"trop\\\": 173, \\\"hiver\\\": 9038, \\\"sont\\\": 1018, \\\"n'aimait\\\": 561, \\\"voiture\\\": 3510, \\\"une\\\": 1278, \\\"pas\\\": 4495, \\\"rouill\\\\u00e9e\\\": 486, \\\"fraises\\\": 5844, \\\"cours\\\": 1927, \\\"j'aime\\\": 966, \\\"fraise\\\": 4848, \\\"bananes\\\": 5844, \\\"va\\\": 355, \\\"aux\\\": 392, \\\"prochain\\\": 1666, \\\"visiter\\\": 908, \\\"pr\\\\u00e9vois\\\": 233, \\\"je\\\": 1548, \\\"belle\\\": 2725, \\\"ses\\\": 402, \\\"animaux\\\": 768, \\\"redout\\\\u00e9s\\\": 190, \\\"\\\\u00e9l\\\\u00e9phants\\\": 64, \\\"\\\\u00e9taient\\\": 357, \\\"vont\\\": 168, \\\"aime\\\": 8870, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9e\\\": 770, \\\"n'aiment\\\": 1111, \\\"i\\\": 150, \\\"comme\\\": 259, \\\"conduit\\\": 1706, \\\"p\\\\u00eache\\\": 4848, \\\"bleue\\\": 504, \\\"nouvelle\\\": 648, \\\"vous\\\": 2541, \\\"aimez\\\": 1053, \\\"cet\\\": 286, \\\"oiseau\\\": 128, \\\"pamplemousses\\\": 552, \\\"pleut\\\": 562, \\\"magnifique\\\": 104, \\\"favori\\\": 3857, \\\"aim\\\\u00e9s\\\": 237, \\\"vos\\\": 225, \\\"chevaux\\\": 64, \\\"n'aimez\\\": 1094, \\\"n'aimons\\\": 97, \\\"souris\\\": 256, \\\"d\\\\u00e9testons\\\": 1001, \\\"dernier\\\": 757, \\\"all\\\\u00e9\\\": 187, \\\"petite\\\": 615, \\\"conduisait\\\": 673, \\\"glaciales\\\": 307, \\\"cheval\\\": 192, \\\"vieille\\\": 647, \\\"chiens\\\": 64, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9s\\\": 383, \\\"blanche\\\": 579, \\\"occup\\\\u00e9e\\\": 836, \\\"nos\\\": 613, \\\"l'\\\\u00e9l\\\\u00e9phant\\\": 64, \\\"nouveau\\\": 502, \\\"noire\\\": 602, \\\"pluies\\\": 367, \\\"traduire\\\": 501, \\\"difficile\\\": 260, \\\"pense\\\": 540, \\\"entre\\\": 540, \\\"qu'il\\\": 393, \\\"portugais\\\": 312, \\\"espagnol\\\": 312, \\\"rouill\\\\u00e9\\\": 454, \\\"bleu\\\": 468, \\\"verte\\\": 628, \\\"grande\\\": 459, \\\"aimait\\\": 707, \\\"amusant\\\": 260, \\\"traduction\\\": 277, \\\"cette\\\": 1239, \\\"vert\\\": 344, \\\"grand\\\": 81, \\\"blanc\\\": 393, \\\"volant\\\": 165, \\\"gros\\\": 258, \\\"o\\\\u00f9\\\": 12, \\\"chien\\\": 192, \\\"leurs\\\": 1072, \\\"pourquoi\\\": 240, \\\"l'automobile\\\": 100, \\\"pourrait\\\": 252, \\\"rendre\\\": 350, \\\"se\\\": 461, \\\"maillot\\\": 173, \\\"pr\\\\u00e9voyons\\\": 232, \\\"grosse\\\": 185, \\\"brillant\\\": 587, \\\"pr\\\\u00e9voient\\\": 75, \\\"mouill\\\\u00e9e\\\": 7, \\\"lui\\\": 70, \\\"d\\\\u00e9tendre\\\": 111, \\\"automobile\\\": 278, \\\"aller\\\": 1180, \\\"pourraient\\\": 126, \\\"mes\\\": 297, \\\"s\\\\u00e8che\\\": 837, \\\"l'oiseau\\\": 64, \\\"pluie\\\": 174, \\\"requins\\\": 64, \\\"noir\\\": 370, \\\"singe\\\": 192, \\\"d\\\\u00e9testait\\\": 87, \\\"dans\\\": 12, \\\"temps\\\": 33, \\\"comment\\\": 67, \\\"lion\\\": 192, \\\"pr\\\\u00e9voit\\\": 75, \\\"ours\\\": 192, \\\"porcelaine\\\": 17, \\\"cl\\\\u00e9mentes\\\": 200, \\\"pla\\\\u00eet\\\": 13, \\\"proches\\\": 20, \\\"brillante\\\": 385, \\\"lapin\\\": 192, \\\"l'ours\\\": 64, \\\"chinois\\\": 312, \\\"quand\\\": 144, \\\"tour\\\": 57, \\\"eiffel\\\": 57, \\\"allons\\\": 45, \\\"l'\\\\u00e9picerie\\\": 57, \\\"voulait\\\": 252, \\\"c\\\\u00e9page\\\": 60, \\\"football\\\": 57, \\\"t\\\": 18, \\\"terrain\\\": 57, \\\"du\\\": 39, \\\"veut\\\": 252, \\\"\\\\u00e9l\\\\u00e9phant\\\": 128, \\\"gel\\\\u00e9\\\": 94, \\\"bien\\\": 77, \\\"enneig\\\\u00e9\\\": 7, \\\"gel\\\\u00e9s\\\": 5, \\\"serpent\\\": 192, \\\"all\\\\u00e9s\\\": 150, \\\"all\\\\u00e9e\\\": 150, \\\"envisage\\\": 360, \\\"peu\\\": 41, \\\"mouill\\\\u00e9\\\": 273, \\\"serpents\\\": 64, \\\"facile\\\": 260, \\\"pensez\\\": 60, \\\"anglais\\\": 312, \\\"fran\\\\u00e7ais\\\": 312, \\\"voulez\\\": 12, \\\"grandes\\\": 16, \\\"avez\\\": 162, \\\"aimeraient\\\": 12, \\\"allez\\\": 45, \\\"chats\\\": 64, \\\"lapins\\\": 64, \\\"visite\\\": 68, \\\"intention\\\": 206, \\\"ont\\\": 194, \\\"n'est\\\": 47, \\\"derni\\\\u00e8re\\\": 24, \\\"voulaient\\\": 126, \\\"singes\\\": 64, \\\"\\\\u00eates\\\": 24, \\\"qu'elle\\\": 26, \\\"vers\\\": 76, \\\"lac\\\": 57, \\\"pousse\\\": 41, \\\"d\\\\u00e9testez\\\": 17, \\\"manguiers\\\": 19, \\\"grands\\\": 9, \\\"l'\\\\u00e9cole\\\": 57, \\\"l'animal\\\": 56, \\\"at\\\": 32, \\\"oiseaux\\\": 64, \\\"ressort\\\": 2, \\\"petits\\\": 10, \\\"n'a\\\": 12, \\\"veulent\\\": 126, \\\"rouille\\\": 32, \\\"frais\\\": 20, \\\"limes\\\": 9, \\\"lions\\\": 64, \\\"douce\\\": 14, \\\"envisagent\\\": 9, \\\"petites\\\": 26, \\\"vais\\\": 24, \\\"durant\\\": 14, \\\"c'est\\\": 17, \\\"cong\\\\u00e9lation\\\": 14, \\\"allions\\\": 1, \\\"voudrait\\\": 24, \\\"d\\\\u00e9tend\\\": 2, \\\"trouv\\\\u00e9\\\": 1, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9es\\\": 16, \\\"conduite\\\": 6, \\\"grosses\\\": 8, \\\"b\\\\u00e9nigne\\\": 8, \\\"avons\\\": 19, \\\"sur\\\": 28, \\\"redout\\\\u00e9e\\\": 2, \\\"etats\\\": 3, \\\"moindres\\\": 7, \\\"n'\\\\u00eates\\\": 3, \\\"vit\\\": 3, \\\"as\\\": 1, \\\"tu\\\": 2, \\\"qui\\\": 2, \\\"faire\\\": 1, \\\"traduis\\\": 2, \\\"favoris\\\": 1, \\\"souvent\\\": 1, \\\"es\\\": 1, \\\"appr\\\\u00e9ci\\\\u00e9\\\": 1, \\\"moteur\\\": 1, \\\"tout\\\": 4}\", \"index_docs\": \"{\\\"11\\\": 28828, \\\"2\\\": 72048, \\\"24\\\": 14398, \\\"67\\\": 7256, \\\"6\\\": 59851, \\\"112\\\": 1867, \\\"1\\\": 104279, \\\"3\\\": 84114, \\\"37\\\": 10741, \\\"35\\\": 11047, \\\"8\\\": 32946, \\\"34\\\": 11052, \\\"50\\\": 8954, \\\"31\\\": 11270, \\\"19\\\": 16323, \\\"4\\\": 33404, \\\"49\\\": 8956, \\\"32\\\": 11267, \\\"69\\\": 6112, \\\"95\\\": 3622, \\\"51\\\": 8951, \\\"12\\\": 28101, \\\"45\\\": 9023, \\\"21\\\": 15908, \\\"101\\\": 3061, \\\"41\\\": 9133, \\\"269\\\": 63, \\\"103\\\": 2916, \\\"48\\\": 8958, \\\"39\\\": 9403, \\\"13\\\": 14357, \\\"40\\\": 9368, \\\"5\\\": 63987, \\\"7\\\": 39038, \\\"82\\\": 4852, \\\"16\\\": 23626, \\\"14\\\": 14038, \\\"83\\\": 4848, \\\"10\\\": 28877, \\\"17\\\": 14722, \\\"84\\\": 4848, \\\"20\\\": 15184, \\\"58\\\": 8458, \\\"29\\\": 11334, \\\"52\\\": 8945, \\\"42\\\": 9100, \\\"65\\\": 7782, \\\"15\\\": 24675, \\\"9\\\": 32618, \\\"125\\\": 1124, \\\"85\\\": 4848, \\\"61\\\": 8319, \\\"43\\\": 9090, \\\"87\\\": 4848, \\\"96\\\": 3566, \\\"86\\\": 4848, \\\"108\\\": 2435, \\\"118\\\": 1356, \\\"133\\\": 972, \\\"149\\\": 645, \\\"110\\\": 1944, \\\"183\\\": 325, \\\"144\\\": 698, \\\"30\\\": 11277, \\\"66\\\": 7658, \\\"109\\\": 2248, \\\"122\\\": 1198, \\\"23\\\": 8334, \\\"213\\\": 192, \\\"115\\\": 1572, \\\"38\\\": 10140, \\\"100\\\": 3131, \\\"76\\\": 5835, \\\"28\\\": 10568, \\\"81\\\": 4886, \\\"53\\\": 8942, \\\"62\\\": 8189, \\\"105\\\": 2707, \\\"36\\\": 10936, \\\"18\\\": 17151, \\\"54\\\": 8910, \\\"57\\\": 8704, \\\"59\\\": 8458, \\\"117\\\": 1437, \\\"26\\\": 13381, \\\"98\\\": 3411, \\\"46\\\": 8999, \\\"33\\\": 11170, \\\"25\\\": 14311, \\\"47\\\": 8995, \\\"139\\\": 834, \\\"22\\\": 14740, \\\"78\\\": 5774, \\\"94\\\": 3743, \\\"77\\\": 5780, \\\"80\\\": 4899, \\\"88\\\": 4848, \\\"64\\\": 7855, \\\"56\\\": 8789, \\\"68\\\": 6387, \\\"70\\\": 5844, \\\"71\\\": 5844, \\\"214\\\": 192, \\\"156\\\": 576, \\\"146\\\": 667, \\\"79\\\": 5100, \\\"63\\\": 7957, \\\"60\\\": 8446, \\\"92\\\": 4008, \\\"126\\\": 1111, \\\"107\\\": 2520, \\\"72\\\": 5844, \\\"73\\\": 5844, \\\"99\\\": 3221, \\\"124\\\": 1126, \\\"184\\\": 324, \\\"134\\\": 972, \\\"27\\\": 12080, \\\"242\\\": 105, \\\"119\\\": 1308, \\\"227\\\": 173, \\\"102\\\": 3016, \\\"226\\\": 173, \\\"44\\\": 9038, \\\"131\\\": 1018, \\\"158\\\": 561, \\\"97\\\": 3510, \\\"120\\\": 1278, \\\"91\\\": 4495, \\\"165\\\": 486, \\\"74\\\": 5844, \\\"111\\\": 1927, \\\"135\\\": 966, \\\"89\\\": 4848, \\\"75\\\": 5844, \\\"180\\\": 355, \\\"173\\\": 392, \\\"114\\\": 1666, \\\"136\\\": 908, \\\"207\\\": 233, \\\"116\\\": 1548, \\\"104\\\": 2725, \\\"170\\\": 402, \\\"141\\\": 768, \\\"222\\\": 190, \\\"256\\\": 64, \\\"179\\\": 357, \\\"229\\\": 168, \\\"55\\\": 8870, \\\"140\\\": 770, \\\"127\\\": 1111, \\\"232\\\": 150, \\\"199\\\": 259, \\\"113\\\": 1706, \\\"90\\\": 4848, \\\"162\\\": 504, \\\"147\\\": 648, \\\"106\\\": 2541, \\\"130\\\": 1053, \\\"192\\\": 286, \\\"236\\\": 128, \\\"159\\\": 552, \\\"157\\\": 562, \\\"243\\\": 104, \\\"93\\\": 3857, \\\"206\\\": 237, \\\"209\\\": 225, \\\"257\\\": 64, \\\"128\\\": 1094, \\\"245\\\": 97, \\\"201\\\": 256, \\\"132\\\": 1001, \\\"142\\\": 757, \\\"223\\\": 187, \\\"151\\\": 615, \\\"145\\\": 673, \\\"190\\\": 307, \\\"215\\\": 192, \\\"148\\\": 647, \\\"258\\\": 64, \\\"175\\\": 383, \\\"155\\\": 579, \\\"138\\\": 836, \\\"152\\\": 613, \\\"259\\\": 64, \\\"163\\\": 502, \\\"153\\\": 602, \\\"177\\\": 367, \\\"164\\\": 501, \\\"196\\\": 260, \\\"160\\\": 540, \\\"161\\\": 540, \\\"171\\\": 393, \\\"186\\\": 312, \\\"185\\\": 312, \\\"169\\\": 454, \\\"166\\\": 468, \\\"150\\\": 628, \\\"168\\\": 459, \\\"143\\\": 707, \\\"197\\\": 260, \\\"194\\\": 277, \\\"121\\\": 1239, \\\"182\\\": 344, \\\"248\\\": 81, \\\"172\\\": 393, \\\"230\\\": 165, \\\"200\\\": 258, \\\"310\\\": 12, \\\"216\\\": 192, \\\"129\\\": 1072, \\\"205\\\": 240, \\\"244\\\": 100, \\\"202\\\": 252, \\\"181\\\": 350, \\\"167\\\": 461, \\\"228\\\": 173, \\\"208\\\": 232, \\\"224\\\": 185, \\\"154\\\": 587, \\\"251\\\": 75, \\\"321\\\": 7, \\\"253\\\": 70, \\\"241\\\": 111, \\\"193\\\": 278, \\\"123\\\": 1180, \\\"238\\\": 126, \\\"191\\\": 297, \\\"137\\\": 837, \\\"260\\\": 64, \\\"225\\\": 174, \\\"261\\\": 64, \\\"176\\\": 370, \\\"217\\\": 192, \\\"247\\\": 87, \\\"311\\\": 12, \\\"286\\\": 33, \\\"255\\\": 67, \\\"218\\\": 192, \\\"252\\\": 75, \\\"219\\\": 192, \\\"301\\\": 17, \\\"211\\\": 200, \\\"309\\\": 13, \\\"296\\\": 20, \\\"174\\\": 385, \\\"220\\\": 192, \\\"262\\\": 64, \\\"187\\\": 312, \\\"235\\\": 144, \\\"272\\\": 57, \\\"273\\\": 57, \\\"281\\\": 45, \\\"274\\\": 57, \\\"203\\\": 252, \\\"270\\\": 60, \\\"276\\\": 57, \\\"300\\\": 18, \\\"275\\\": 57, \\\"285\\\": 39, \\\"204\\\": 252, \\\"237\\\": 128, \\\"246\\\": 94, \\\"249\\\": 77, \\\"322\\\": 7, \\\"325\\\": 5, \\\"221\\\": 192, \\\"233\\\": 150, \\\"234\\\": 150, \\\"178\\\": 360, \\\"283\\\": 41, \\\"195\\\": 273, \\\"263\\\": 64, \\\"198\\\": 260, \\\"271\\\": 60, \\\"188\\\": 312, \\\"189\\\": 312, \\\"312\\\": 12, \\\"304\\\": 16, \\\"231\\\": 162, \\\"313\\\": 12, \\\"282\\\": 45, \\\"264\\\": 64, \\\"265\\\": 64, \\\"254\\\": 68, \\\"210\\\": 206, \\\"212\\\": 194, \\\"280\\\": 47, \\\"292\\\": 24, \\\"239\\\": 126, \\\"266\\\": 64, \\\"293\\\": 24, \\\"290\\\": 26, \\\"250\\\": 76, \\\"277\\\": 57, \\\"284\\\": 41, \\\"302\\\": 17, \\\"298\\\": 19, \\\"316\\\": 9, \\\"278\\\": 57, \\\"279\\\": 56, \\\"287\\\": 32, \\\"267\\\": 64, \\\"330\\\": 2, \\\"315\\\": 10, \\\"314\\\": 12, \\\"240\\\": 126, \\\"288\\\": 32, \\\"297\\\": 20, \\\"317\\\": 9, \\\"268\\\": 64, \\\"306\\\": 14, \\\"318\\\": 9, \\\"291\\\": 26, \\\"294\\\": 24, \\\"307\\\": 14, \\\"303\\\": 17, \\\"308\\\": 14, \\\"337\\\": 1, \\\"295\\\": 24, \\\"331\\\": 2, \\\"338\\\": 1, \\\"305\\\": 16, \\\"324\\\": 6, \\\"319\\\": 8, \\\"320\\\": 8, \\\"299\\\": 19, \\\"289\\\": 28, \\\"332\\\": 2, \\\"327\\\": 3, \\\"323\\\": 7, \\\"328\\\": 3, \\\"329\\\": 3, \\\"339\\\": 1, \\\"333\\\": 2, \\\"334\\\": 2, \\\"340\\\": 1, \\\"335\\\": 2, \\\"341\\\": 1, \\\"342\\\": 1, \\\"343\\\": 1, \\\"336\\\": 1, \\\"344\\\": 1, \\\"326\\\": 4}\", \"index_word\": \"{\\\"1\\\": \\\"est\\\", \\\"2\\\": \\\"en\\\", \\\"3\\\": \\\"il\\\", \\\"4\\\": \\\"les\\\", \\\"5\\\": \\\"mais\\\", \\\"6\\\": \\\"et\\\", \\\"7\\\": \\\"la\\\", \\\"8\\\": \\\"parfois\\\", \\\"9\\\": \\\"jamais\\\", \\\"10\\\": \\\"le\\\", \\\"11\\\": \\\"l'\\\", \\\"12\\\": \\\"g\\\\u00e9n\\\\u00e9ralement\\\", \\\"13\\\": \\\"moins\\\", \\\"14\\\": \\\"aim\\\\u00e9\\\", \\\"15\\\": \\\"au\\\", \\\"16\\\": \\\"fruit\\\", \\\"17\\\": \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9\\\", \\\"18\\\": \\\"agr\\\\u00e9able\\\", \\\"19\\\": \\\"froid\\\", \\\"20\\\": \\\"son\\\", \\\"21\\\": \\\"chaud\\\", \\\"22\\\": \\\"de\\\", \\\"23\\\": \\\"plus\\\", \\\"24\\\": \\\"automne\\\", \\\"25\\\": \\\"mois\\\", \\\"26\\\": \\\"\\\\u00e0\\\", \\\"27\\\": \\\"elle\\\", \\\"28\\\": \\\"citrons\\\", \\\"29\\\": \\\"paris\\\", \\\"30\\\": \\\"inde\\\", \\\"31\\\": \\\"unis\\\", \\\"32\\\": \\\"\\\\u00e9tats\\\", \\\"33\\\": \\\"france\\\", \\\"34\\\": \\\"jersey\\\", \\\"35\\\": \\\"new\\\", \\\"36\\\": \\\"chine\\\", \\\"37\\\": \\\"pendant\\\", \\\"38\\\": \\\"pamplemousse\\\", \\\"39\\\": \\\"mon\\\", \\\"40\\\": \\\"votre\\\", \\\"41\\\": \\\"juin\\\", \\\"42\\\": \\\"printemps\\\", \\\"43\\\": \\\"janvier\\\", \\\"44\\\": \\\"hiver\\\", \\\"45\\\": \\\"mars\\\", \\\"46\\\": \\\"\\\\u00e9t\\\\u00e9\\\", \\\"47\\\": \\\"mai\\\", \\\"48\\\": \\\"septembre\\\", \\\"49\\\": \\\"juillet\\\", \\\"50\\\": \\\"avril\\\", \\\"51\\\": \\\"novembre\\\", \\\"52\\\": \\\"d\\\\u00e9cembre\\\", \\\"53\\\": \\\"f\\\\u00e9vrier\\\", \\\"54\\\": \\\"octobre\\\", \\\"55\\\": \\\"aime\\\", \\\"56\\\": \\\"ao\\\\u00fbt\\\", \\\"57\\\": \\\"merveilleux\\\", \\\"58\\\": \\\"relaxant\\\", \\\"59\\\": \\\"doux\\\", \\\"60\\\": \\\"humide\\\", \\\"61\\\": \\\"notre\\\", \\\"62\\\": \\\"californie\\\", \\\"63\\\": \\\"sec\\\", \\\"64\\\": \\\"leur\\\", \\\"65\\\": \\\"occup\\\\u00e9\\\", \\\"66\\\": \\\"pluvieux\\\", \\\"67\\\": \\\"calme\\\", \\\"68\\\": \\\"beau\\\", \\\"69\\\": \\\"habituellement\\\", \\\"70\\\": \\\"pommes\\\", \\\"71\\\": \\\"p\\\\u00eaches\\\", \\\"72\\\": \\\"oranges\\\", \\\"73\\\": \\\"poires\\\", \\\"74\\\": \\\"fraises\\\", \\\"75\\\": \\\"bananes\\\", \\\"76\\\": \\\"verts\\\", \\\"77\\\": \\\"raisins\\\", \\\"78\\\": \\\"mangues\\\", \\\"79\\\": \\\"d'\\\", \\\"80\\\": \\\"mangue\\\", \\\"81\\\": \\\"gel\\\", \\\"82\\\": \\\"raisin\\\", \\\"83\\\": \\\"pomme\\\", \\\"84\\\": \\\"l'orange\\\", \\\"85\\\": \\\"citron\\\", \\\"86\\\": \\\"chaux\\\", \\\"87\\\": \\\"banane\\\", \\\"88\\\": \\\"poire\\\", \\\"89\\\": \\\"fraise\\\", \\\"90\\\": \\\"p\\\\u00eache\\\", \\\"91\\\": \\\"pas\\\", \\\"92\\\": \\\"enneig\\\\u00e9e\\\", \\\"93\\\": \\\"favori\\\", \\\"94\\\": \\\"d\\\\u00e9teste\\\", \\\"95\\\": \\\"g\\\\u00e8le\\\", \\\"96\\\": \\\"fruits\\\", \\\"97\\\": \\\"voiture\\\", \\\"98\\\": \\\"l'automne\\\", \\\"99\\\": \\\"ils\\\", \\\"100\\\": \\\"n'aime\\\", \\\"101\\\": \\\"california\\\", \\\"102\\\": \\\"neige\\\", \\\"103\\\": \\\"fait\\\", \\\"104\\\": \\\"belle\\\", \\\"105\\\": \\\"ne\\\", \\\"106\\\": \\\"vous\\\", \\\"107\\\": \\\"nous\\\", \\\"108\\\": \\\"des\\\", \\\"109\\\": \\\"animal\\\", \\\"110\\\": \\\"camion\\\", \\\"111\\\": \\\"cours\\\", \\\"112\\\": \\\"neigeux\\\", \\\"113\\\": \\\"conduit\\\", \\\"114\\\": \\\"prochain\\\", \\\"115\\\": \\\"ce\\\", \\\"116\\\": \\\"je\\\", \\\"117\\\": \\\"tranquille\\\", \\\"118\\\": \\\"a\\\", \\\"119\\\": \\\"cher\\\", \\\"120\\\": \\\"une\\\", \\\"121\\\": \\\"cette\\\", \\\"122\\\": \\\"\\\\u00e9tait\\\", \\\"123\\\": \\\"aller\\\", \\\"124\\\": \\\"aiment\\\", \\\"125\\\": \\\"chaude\\\", \\\"126\\\": \\\"aimons\\\", \\\"127\\\": \\\"n'aiment\\\", \\\"128\\\": \\\"n'aimez\\\", \\\"129\\\": \\\"leurs\\\", \\\"130\\\": \\\"aimez\\\", \\\"131\\\": \\\"sont\\\", \\\"132\\\": \\\"d\\\\u00e9testons\\\", \\\"133\\\": \\\"jaune\\\", \\\"134\\\": \\\"rouge\\\", \\\"135\\\": \\\"j'aime\\\", \\\"136\\\": \\\"visiter\\\", \\\"137\\\": \\\"s\\\\u00e8che\\\", \\\"138\\\": \\\"occup\\\\u00e9e\\\", \\\"139\\\": \\\"frisquet\\\", \\\"140\\\": \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9e\\\", \\\"141\\\": \\\"animaux\\\", \\\"142\\\": \\\"dernier\\\", \\\"143\\\": \\\"aimait\\\", \\\"144\\\": \\\"un\\\", \\\"145\\\": \\\"conduisait\\\", \\\"146\\\": \\\"que\\\", \\\"147\\\": \\\"nouvelle\\\", \\\"148\\\": \\\"vieille\\\", \\\"149\\\": \\\"vu\\\", \\\"150\\\": \\\"verte\\\", \\\"151\\\": \\\"petite\\\", \\\"152\\\": \\\"nos\\\", \\\"153\\\": \\\"noire\\\", \\\"154\\\": \\\"brillant\\\", \\\"155\\\": \\\"blanche\\\", \\\"156\\\": \\\"redout\\\\u00e9\\\", \\\"157\\\": \\\"pleut\\\", \\\"158\\\": \\\"n'aimait\\\", \\\"159\\\": \\\"pamplemousses\\\", \\\"160\\\": \\\"pense\\\", \\\"161\\\": \\\"entre\\\", \\\"162\\\": \\\"bleue\\\", \\\"163\\\": \\\"nouveau\\\", \\\"164\\\": \\\"traduire\\\", \\\"165\\\": \\\"rouill\\\\u00e9e\\\", \\\"166\\\": \\\"bleu\\\", \\\"167\\\": \\\"se\\\", \\\"168\\\": \\\"grande\\\", \\\"169\\\": \\\"rouill\\\\u00e9\\\", \\\"170\\\": \\\"ses\\\", \\\"171\\\": \\\"qu'il\\\", \\\"172\\\": \\\"blanc\\\", \\\"173\\\": \\\"aux\\\", \\\"174\\\": \\\"brillante\\\", \\\"175\\\": \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9s\\\", \\\"176\\\": \\\"noir\\\", \\\"177\\\": \\\"pluies\\\", \\\"178\\\": \\\"envisage\\\", \\\"179\\\": \\\"\\\\u00e9taient\\\", \\\"180\\\": \\\"va\\\", \\\"181\\\": \\\"rendre\\\", \\\"182\\\": \\\"vert\\\", \\\"183\\\": \\\"vieux\\\", \\\"184\\\": \\\"petit\\\", \\\"185\\\": \\\"espagnol\\\", \\\"186\\\": \\\"portugais\\\", \\\"187\\\": \\\"chinois\\\", \\\"188\\\": \\\"anglais\\\", \\\"189\\\": \\\"fran\\\\u00e7ais\\\", \\\"190\\\": \\\"glaciales\\\", \\\"191\\\": \\\"mes\\\", \\\"192\\\": \\\"cet\\\", \\\"193\\\": \\\"automobile\\\", \\\"194\\\": \\\"traduction\\\", \\\"195\\\": \\\"mouill\\\\u00e9\\\", \\\"196\\\": \\\"difficile\\\", \\\"197\\\": \\\"amusant\\\", \\\"198\\\": \\\"facile\\\", \\\"199\\\": \\\"comme\\\", \\\"200\\\": \\\"gros\\\", \\\"201\\\": \\\"souris\\\", \\\"202\\\": \\\"pourrait\\\", \\\"203\\\": \\\"voulait\\\", \\\"204\\\": \\\"veut\\\", \\\"205\\\": \\\"pourquoi\\\", \\\"206\\\": \\\"aim\\\\u00e9s\\\", \\\"207\\\": \\\"pr\\\\u00e9vois\\\", \\\"208\\\": \\\"pr\\\\u00e9voyons\\\", \\\"209\\\": \\\"vos\\\", \\\"210\\\": \\\"intention\\\", \\\"211\\\": \\\"cl\\\\u00e9mentes\\\", \\\"212\\\": \\\"ont\\\", \\\"213\\\": \\\"chat\\\", \\\"214\\\": \\\"requin\\\", \\\"215\\\": \\\"cheval\\\", \\\"216\\\": \\\"chien\\\", \\\"217\\\": \\\"singe\\\", \\\"218\\\": \\\"lion\\\", \\\"219\\\": \\\"ours\\\", \\\"220\\\": \\\"lapin\\\", \\\"221\\\": \\\"serpent\\\", \\\"222\\\": \\\"redout\\\\u00e9s\\\", \\\"223\\\": \\\"all\\\\u00e9\\\", \\\"224\\\": \\\"grosse\\\", \\\"225\\\": \\\"pluie\\\", \\\"226\\\": \\\"trop\\\", \\\"227\\\": \\\"monde\\\", \\\"228\\\": \\\"maillot\\\", \\\"229\\\": \\\"vont\\\", \\\"230\\\": \\\"volant\\\", \\\"231\\\": \\\"avez\\\", \\\"232\\\": \\\"i\\\", \\\"233\\\": \\\"all\\\\u00e9s\\\", \\\"234\\\": \\\"all\\\\u00e9e\\\", \\\"235\\\": \\\"quand\\\", \\\"236\\\": \\\"oiseau\\\", \\\"237\\\": \\\"\\\\u00e9l\\\\u00e9phant\\\", \\\"238\\\": \\\"pourraient\\\", \\\"239\\\": \\\"voulaient\\\", \\\"240\\\": \\\"veulent\\\", \\\"241\\\": \\\"d\\\\u00e9tendre\\\", \\\"242\\\": \\\"aim\\\\u00e9e\\\", \\\"243\\\": \\\"magnifique\\\", \\\"244\\\": \\\"l'automobile\\\", \\\"245\\\": \\\"n'aimons\\\", \\\"246\\\": \\\"gel\\\\u00e9\\\", \\\"247\\\": \\\"d\\\\u00e9testait\\\", \\\"248\\\": \\\"grand\\\", \\\"249\\\": \\\"bien\\\", \\\"250\\\": \\\"vers\\\", \\\"251\\\": \\\"pr\\\\u00e9voient\\\", \\\"252\\\": \\\"pr\\\\u00e9voit\\\", \\\"253\\\": \\\"lui\\\", \\\"254\\\": \\\"visite\\\", \\\"255\\\": \\\"comment\\\", \\\"256\\\": \\\"\\\\u00e9l\\\\u00e9phants\\\", \\\"257\\\": \\\"chevaux\\\", \\\"258\\\": \\\"chiens\\\", \\\"259\\\": \\\"l'\\\\u00e9l\\\\u00e9phant\\\", \\\"260\\\": \\\"l'oiseau\\\", \\\"261\\\": \\\"requins\\\", \\\"262\\\": \\\"l'ours\\\", \\\"263\\\": \\\"serpents\\\", \\\"264\\\": \\\"chats\\\", \\\"265\\\": \\\"lapins\\\", \\\"266\\\": \\\"singes\\\", \\\"267\\\": \\\"oiseaux\\\", \\\"268\\\": \\\"lions\\\", \\\"269\\\": \\\"l\\\\u00e9g\\\\u00e8re\\\", \\\"270\\\": \\\"c\\\\u00e9page\\\", \\\"271\\\": \\\"pensez\\\", \\\"272\\\": \\\"tour\\\", \\\"273\\\": \\\"eiffel\\\", \\\"274\\\": \\\"l'\\\\u00e9picerie\\\", \\\"275\\\": \\\"terrain\\\", \\\"276\\\": \\\"football\\\", \\\"277\\\": \\\"lac\\\", \\\"278\\\": \\\"l'\\\\u00e9cole\\\", \\\"279\\\": \\\"l'animal\\\", \\\"280\\\": \\\"n'est\\\", \\\"281\\\": \\\"allons\\\", \\\"282\\\": \\\"allez\\\", \\\"283\\\": \\\"peu\\\", \\\"284\\\": \\\"pousse\\\", \\\"285\\\": \\\"du\\\", \\\"286\\\": \\\"temps\\\", \\\"287\\\": \\\"at\\\", \\\"288\\\": \\\"rouille\\\", \\\"289\\\": \\\"sur\\\", \\\"290\\\": \\\"qu'elle\\\", \\\"291\\\": \\\"petites\\\", \\\"292\\\": \\\"derni\\\\u00e8re\\\", \\\"293\\\": \\\"\\\\u00eates\\\", \\\"294\\\": \\\"vais\\\", \\\"295\\\": \\\"voudrait\\\", \\\"296\\\": \\\"proches\\\", \\\"297\\\": \\\"frais\\\", \\\"298\\\": \\\"manguiers\\\", \\\"299\\\": \\\"avons\\\", \\\"300\\\": \\\"t\\\", \\\"301\\\": \\\"porcelaine\\\", \\\"302\\\": \\\"d\\\\u00e9testez\\\", \\\"303\\\": \\\"c'est\\\", \\\"304\\\": \\\"grandes\\\", \\\"305\\\": \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9es\\\", \\\"306\\\": \\\"douce\\\", \\\"307\\\": \\\"durant\\\", \\\"308\\\": \\\"cong\\\\u00e9lation\\\", \\\"309\\\": \\\"pla\\\\u00eet\\\", \\\"310\\\": \\\"o\\\\u00f9\\\", \\\"311\\\": \\\"dans\\\", \\\"312\\\": \\\"voulez\\\", \\\"313\\\": \\\"aimeraient\\\", \\\"314\\\": \\\"n'a\\\", \\\"315\\\": \\\"petits\\\", \\\"316\\\": \\\"grands\\\", \\\"317\\\": \\\"limes\\\", \\\"318\\\": \\\"envisagent\\\", \\\"319\\\": \\\"grosses\\\", \\\"320\\\": \\\"b\\\\u00e9nigne\\\", \\\"321\\\": \\\"mouill\\\\u00e9e\\\", \\\"322\\\": \\\"enneig\\\\u00e9\\\", \\\"323\\\": \\\"moindres\\\", \\\"324\\\": \\\"conduite\\\", \\\"325\\\": \\\"gel\\\\u00e9s\\\", \\\"326\\\": \\\"tout\\\", \\\"327\\\": \\\"etats\\\", \\\"328\\\": \\\"n'\\\\u00eates\\\", \\\"329\\\": \\\"vit\\\", \\\"330\\\": \\\"ressort\\\", \\\"331\\\": \\\"d\\\\u00e9tend\\\", \\\"332\\\": \\\"redout\\\\u00e9e\\\", \\\"333\\\": \\\"tu\\\", \\\"334\\\": \\\"qui\\\", \\\"335\\\": \\\"traduis\\\", \\\"336\\\": \\\"appr\\\\u00e9ci\\\\u00e9\\\", \\\"337\\\": \\\"allions\\\", \\\"338\\\": \\\"trouv\\\\u00e9\\\", \\\"339\\\": \\\"as\\\", \\\"340\\\": \\\"faire\\\", \\\"341\\\": \\\"favoris\\\", \\\"342\\\": \\\"souvent\\\", \\\"343\\\": \\\"es\\\", \\\"344\\\": \\\"moteur\\\"}\", \"word_index\": \"{\\\"est\\\": 1, \\\"en\\\": 2, \\\"il\\\": 3, \\\"les\\\": 4, \\\"mais\\\": 5, \\\"et\\\": 6, \\\"la\\\": 7, \\\"parfois\\\": 8, \\\"jamais\\\": 9, \\\"le\\\": 10, \\\"l'\\\": 11, \\\"g\\\\u00e9n\\\\u00e9ralement\\\": 12, \\\"moins\\\": 13, \\\"aim\\\\u00e9\\\": 14, \\\"au\\\": 15, \\\"fruit\\\": 16, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9\\\": 17, \\\"agr\\\\u00e9able\\\": 18, \\\"froid\\\": 19, \\\"son\\\": 20, \\\"chaud\\\": 21, \\\"de\\\": 22, \\\"plus\\\": 23, \\\"automne\\\": 24, \\\"mois\\\": 25, \\\"\\\\u00e0\\\": 26, \\\"elle\\\": 27, \\\"citrons\\\": 28, \\\"paris\\\": 29, \\\"inde\\\": 30, \\\"unis\\\": 31, \\\"\\\\u00e9tats\\\": 32, \\\"france\\\": 33, \\\"jersey\\\": 34, \\\"new\\\": 35, \\\"chine\\\": 36, \\\"pendant\\\": 37, \\\"pamplemousse\\\": 38, \\\"mon\\\": 39, \\\"votre\\\": 40, \\\"juin\\\": 41, \\\"printemps\\\": 42, \\\"janvier\\\": 43, \\\"hiver\\\": 44, \\\"mars\\\": 45, \\\"\\\\u00e9t\\\\u00e9\\\": 46, \\\"mai\\\": 47, \\\"septembre\\\": 48, \\\"juillet\\\": 49, \\\"avril\\\": 50, \\\"novembre\\\": 51, \\\"d\\\\u00e9cembre\\\": 52, \\\"f\\\\u00e9vrier\\\": 53, \\\"octobre\\\": 54, \\\"aime\\\": 55, \\\"ao\\\\u00fbt\\\": 56, \\\"merveilleux\\\": 57, \\\"relaxant\\\": 58, \\\"doux\\\": 59, \\\"humide\\\": 60, \\\"notre\\\": 61, \\\"californie\\\": 62, \\\"sec\\\": 63, \\\"leur\\\": 64, \\\"occup\\\\u00e9\\\": 65, \\\"pluvieux\\\": 66, \\\"calme\\\": 67, \\\"beau\\\": 68, \\\"habituellement\\\": 69, \\\"pommes\\\": 70, \\\"p\\\\u00eaches\\\": 71, \\\"oranges\\\": 72, \\\"poires\\\": 73, \\\"fraises\\\": 74, \\\"bananes\\\": 75, \\\"verts\\\": 76, \\\"raisins\\\": 77, \\\"mangues\\\": 78, \\\"d'\\\": 79, \\\"mangue\\\": 80, \\\"gel\\\": 81, \\\"raisin\\\": 82, \\\"pomme\\\": 83, \\\"l'orange\\\": 84, \\\"citron\\\": 85, \\\"chaux\\\": 86, \\\"banane\\\": 87, \\\"poire\\\": 88, \\\"fraise\\\": 89, \\\"p\\\\u00eache\\\": 90, \\\"pas\\\": 91, \\\"enneig\\\\u00e9e\\\": 92, \\\"favori\\\": 93, \\\"d\\\\u00e9teste\\\": 94, \\\"g\\\\u00e8le\\\": 95, \\\"fruits\\\": 96, \\\"voiture\\\": 97, \\\"l'automne\\\": 98, \\\"ils\\\": 99, \\\"n'aime\\\": 100, \\\"california\\\": 101, \\\"neige\\\": 102, \\\"fait\\\": 103, \\\"belle\\\": 104, \\\"ne\\\": 105, \\\"vous\\\": 106, \\\"nous\\\": 107, \\\"des\\\": 108, \\\"animal\\\": 109, \\\"camion\\\": 110, \\\"cours\\\": 111, \\\"neigeux\\\": 112, \\\"conduit\\\": 113, \\\"prochain\\\": 114, \\\"ce\\\": 115, \\\"je\\\": 116, \\\"tranquille\\\": 117, \\\"a\\\": 118, \\\"cher\\\": 119, \\\"une\\\": 120, \\\"cette\\\": 121, \\\"\\\\u00e9tait\\\": 122, \\\"aller\\\": 123, \\\"aiment\\\": 124, \\\"chaude\\\": 125, \\\"aimons\\\": 126, \\\"n'aiment\\\": 127, \\\"n'aimez\\\": 128, \\\"leurs\\\": 129, \\\"aimez\\\": 130, \\\"sont\\\": 131, \\\"d\\\\u00e9testons\\\": 132, \\\"jaune\\\": 133, \\\"rouge\\\": 134, \\\"j'aime\\\": 135, \\\"visiter\\\": 136, \\\"s\\\\u00e8che\\\": 137, \\\"occup\\\\u00e9e\\\": 138, \\\"frisquet\\\": 139, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9e\\\": 140, \\\"animaux\\\": 141, \\\"dernier\\\": 142, \\\"aimait\\\": 143, \\\"un\\\": 144, \\\"conduisait\\\": 145, \\\"que\\\": 146, \\\"nouvelle\\\": 147, \\\"vieille\\\": 148, \\\"vu\\\": 149, \\\"verte\\\": 150, \\\"petite\\\": 151, \\\"nos\\\": 152, \\\"noire\\\": 153, \\\"brillant\\\": 154, \\\"blanche\\\": 155, \\\"redout\\\\u00e9\\\": 156, \\\"pleut\\\": 157, \\\"n'aimait\\\": 158, \\\"pamplemousses\\\": 159, \\\"pense\\\": 160, \\\"entre\\\": 161, \\\"bleue\\\": 162, \\\"nouveau\\\": 163, \\\"traduire\\\": 164, \\\"rouill\\\\u00e9e\\\": 165, \\\"bleu\\\": 166, \\\"se\\\": 167, \\\"grande\\\": 168, \\\"rouill\\\\u00e9\\\": 169, \\\"ses\\\": 170, \\\"qu'il\\\": 171, \\\"blanc\\\": 172, \\\"aux\\\": 173, \\\"brillante\\\": 174, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9s\\\": 175, \\\"noir\\\": 176, \\\"pluies\\\": 177, \\\"envisage\\\": 178, \\\"\\\\u00e9taient\\\": 179, \\\"va\\\": 180, \\\"rendre\\\": 181, \\\"vert\\\": 182, \\\"vieux\\\": 183, \\\"petit\\\": 184, \\\"espagnol\\\": 185, \\\"portugais\\\": 186, \\\"chinois\\\": 187, \\\"anglais\\\": 188, \\\"fran\\\\u00e7ais\\\": 189, \\\"glaciales\\\": 190, \\\"mes\\\": 191, \\\"cet\\\": 192, \\\"automobile\\\": 193, \\\"traduction\\\": 194, \\\"mouill\\\\u00e9\\\": 195, \\\"difficile\\\": 196, \\\"amusant\\\": 197, \\\"facile\\\": 198, \\\"comme\\\": 199, \\\"gros\\\": 200, \\\"souris\\\": 201, \\\"pourrait\\\": 202, \\\"voulait\\\": 203, \\\"veut\\\": 204, \\\"pourquoi\\\": 205, \\\"aim\\\\u00e9s\\\": 206, \\\"pr\\\\u00e9vois\\\": 207, \\\"pr\\\\u00e9voyons\\\": 208, \\\"vos\\\": 209, \\\"intention\\\": 210, \\\"cl\\\\u00e9mentes\\\": 211, \\\"ont\\\": 212, \\\"chat\\\": 213, \\\"requin\\\": 214, \\\"cheval\\\": 215, \\\"chien\\\": 216, \\\"singe\\\": 217, \\\"lion\\\": 218, \\\"ours\\\": 219, \\\"lapin\\\": 220, \\\"serpent\\\": 221, \\\"redout\\\\u00e9s\\\": 222, \\\"all\\\\u00e9\\\": 223, \\\"grosse\\\": 224, \\\"pluie\\\": 225, \\\"trop\\\": 226, \\\"monde\\\": 227, \\\"maillot\\\": 228, \\\"vont\\\": 229, \\\"volant\\\": 230, \\\"avez\\\": 231, \\\"i\\\": 232, \\\"all\\\\u00e9s\\\": 233, \\\"all\\\\u00e9e\\\": 234, \\\"quand\\\": 235, \\\"oiseau\\\": 236, \\\"\\\\u00e9l\\\\u00e9phant\\\": 237, \\\"pourraient\\\": 238, \\\"voulaient\\\": 239, \\\"veulent\\\": 240, \\\"d\\\\u00e9tendre\\\": 241, \\\"aim\\\\u00e9e\\\": 242, \\\"magnifique\\\": 243, \\\"l'automobile\\\": 244, \\\"n'aimons\\\": 245, \\\"gel\\\\u00e9\\\": 246, \\\"d\\\\u00e9testait\\\": 247, \\\"grand\\\": 248, \\\"bien\\\": 249, \\\"vers\\\": 250, \\\"pr\\\\u00e9voient\\\": 251, \\\"pr\\\\u00e9voit\\\": 252, \\\"lui\\\": 253, \\\"visite\\\": 254, \\\"comment\\\": 255, \\\"\\\\u00e9l\\\\u00e9phants\\\": 256, \\\"chevaux\\\": 257, \\\"chiens\\\": 258, \\\"l'\\\\u00e9l\\\\u00e9phant\\\": 259, \\\"l'oiseau\\\": 260, \\\"requins\\\": 261, \\\"l'ours\\\": 262, \\\"serpents\\\": 263, \\\"chats\\\": 264, \\\"lapins\\\": 265, \\\"singes\\\": 266, \\\"oiseaux\\\": 267, \\\"lions\\\": 268, \\\"l\\\\u00e9g\\\\u00e8re\\\": 269, \\\"c\\\\u00e9page\\\": 270, \\\"pensez\\\": 271, \\\"tour\\\": 272, \\\"eiffel\\\": 273, \\\"l'\\\\u00e9picerie\\\": 274, \\\"terrain\\\": 275, \\\"football\\\": 276, \\\"lac\\\": 277, \\\"l'\\\\u00e9cole\\\": 278, \\\"l'animal\\\": 279, \\\"n'est\\\": 280, \\\"allons\\\": 281, \\\"allez\\\": 282, \\\"peu\\\": 283, \\\"pousse\\\": 284, \\\"du\\\": 285, \\\"temps\\\": 286, \\\"at\\\": 287, \\\"rouille\\\": 288, \\\"sur\\\": 289, \\\"qu'elle\\\": 290, \\\"petites\\\": 291, \\\"derni\\\\u00e8re\\\": 292, \\\"\\\\u00eates\\\": 293, \\\"vais\\\": 294, \\\"voudrait\\\": 295, \\\"proches\\\": 296, \\\"frais\\\": 297, \\\"manguiers\\\": 298, \\\"avons\\\": 299, \\\"t\\\": 300, \\\"porcelaine\\\": 301, \\\"d\\\\u00e9testez\\\": 302, \\\"c'est\\\": 303, \\\"grandes\\\": 304, \\\"pr\\\\u00e9f\\\\u00e9r\\\\u00e9es\\\": 305, \\\"douce\\\": 306, \\\"durant\\\": 307, \\\"cong\\\\u00e9lation\\\": 308, \\\"pla\\\\u00eet\\\": 309, \\\"o\\\\u00f9\\\": 310, \\\"dans\\\": 311, \\\"voulez\\\": 312, \\\"aimeraient\\\": 313, \\\"n'a\\\": 314, \\\"petits\\\": 315, \\\"grands\\\": 316, \\\"limes\\\": 317, \\\"envisagent\\\": 318, \\\"grosses\\\": 319, \\\"b\\\\u00e9nigne\\\": 320, \\\"mouill\\\\u00e9e\\\": 321, \\\"enneig\\\\u00e9\\\": 322, \\\"moindres\\\": 323, \\\"conduite\\\": 324, \\\"gel\\\\u00e9s\\\": 325, \\\"tout\\\": 326, \\\"etats\\\": 327, \\\"n'\\\\u00eates\\\": 328, \\\"vit\\\": 329, \\\"ressort\\\": 330, \\\"d\\\\u00e9tend\\\": 331, \\\"redout\\\\u00e9e\\\": 332, \\\"tu\\\": 333, \\\"qui\\\": 334, \\\"traduis\\\": 335, \\\"appr\\\\u00e9ci\\\\u00e9\\\": 336, \\\"allions\\\": 337, \\\"trouv\\\\u00e9\\\": 338, \\\"as\\\": 339, \\\"faire\\\": 340, \\\"favoris\\\": 341, \\\"souvent\\\": 342, \\\"es\\\": 343, \\\"moteur\\\": 344}\"}}"

Task 2/gui.py

@@ -0,0 +1,218 @@
+# Import libraries
+import tkinter as tk
+from tkinter import ttk, messagebox
+
+from keras.layers import TextVectorization
+import re
+import tensorflow.strings as tf_strings
+import json
+import string
+from keras.models import load_model
+import tensorflow as tf
+from keras.preprocessing.text import tokenizer_from_json
+from keras.utils import pad_sequences
+import numpy as np
+import difflib
+
+# English to Spanish translation
+strip_chars = string.punctuation + "¿"
+strip_chars = strip_chars.replace("[", "")
+strip_chars = strip_chars.replace("]", "")
+
+def custom_standardization(input_string):
+    lowercase = tf_strings.lower(input_string)
+    return tf_strings.regex_replace(lowercase, f"[{re.escape(strip_chars)}]", "")
+
+# Load the English vectorization layer configuration
+with open('eng_vectorization_config.json') as json_file:
+    eng_vectorization_config = json.load(json_file)
+
+# Recreate the English vectorization layer with basic configuration
+eng_vectorization = TextVectorization(
+    max_tokens=eng_vectorization_config['max_tokens'],
+    output_mode=eng_vectorization_config['output_mode'],
+    output_sequence_length=eng_vectorization_config['output_sequence_length']
+)
+
+# Apply the custom standardization function
+eng_vectorization.standardize = custom_standardization
+
+# Load the Spanish vectorization layer configuration
+with open('spa_vectorization_config.json') as json_file:
+    spa_vectorization_config = json.load(json_file)
+
+# Recreate the Spanish vectorization layer with basic configuration
+spa_vectorization = TextVectorization(
+    max_tokens=spa_vectorization_config['max_tokens'],
+    output_mode=spa_vectorization_config['output_mode'],
+    output_sequence_length=spa_vectorization_config['output_sequence_length'],
+    standardize=custom_standardization
+)
+
+# Load and set the English vocabulary
+with open('eng_vocab.json') as json_file:
+    eng_vocab = json.load(json_file)
+    eng_vectorization.set_vocabulary(eng_vocab)
+
+# Load and set the Spanish vocabulary
+with open('spa_vocab.json') as json_file:
+    spa_vocab = json.load(json_file)
+    spa_vectorization.set_vocabulary(spa_vocab)
+
+# Load the Spanish model
+transformer = load_model('transformer_model')
+
+spa_index_lookup = dict(zip(range(len(spa_vocab)), spa_vocab))
+max_decoded_sentence_length = 20
+
+# Initialize list to track incorrect words
+incorrect_words = []
+
+def beam_search_decode(input_sentence, beam_width=3):
+    tokenized_input_sentence = eng_vectorization([input_sentence])
+    decoded_sentences = [("[start]", 0.0)]
+    
+    for i in range(max_decoded_sentence_length):
+        all_candidates = []
+        for decoded_sentence, score in decoded_sentences:
+            tokenized_target_sentence = spa_vectorization([decoded_sentence])[:, :-1]
+            predictions = transformer([tokenized_input_sentence, tokenized_target_sentence])
+            top_k = tf.math.top_k(predictions[0, i, :], k=beam_width)
+            
+            for j in range(beam_width):
+                predicted_token_index = top_k.indices[j].numpy()
+                predicted_token = spa_index_lookup[predicted_token_index]
+                candidate = (decoded_sentence + " " + predicted_token, score + top_k.values[j].numpy())
+                all_candidates.append(candidate)
+        
+        ordered = sorted(all_candidates, key=lambda x: x[1], reverse=True)
+        decoded_sentences = ordered[:beam_width]
+        
+        if all(sentence[0].endswith("[end]") for sentence in decoded_sentences):
+            break
+    
+    return decoded_sentences[0][0]
+
+# English to French translation
+# Load French model
+model = load_model('english_to_french_model')
+
+# Load Tokenizer
+with open('english_tokenizer.json') as f:
+    data = json.load(f)
+    english_tokenizer = tokenizer_from_json(data)
+    
+with open('french_tokenizer.json') as f:
+    data = json.load(f)
+    french_tokenizer = tokenizer_from_json(data)
+    
+# Load max length
+with open('sequence_length.json') as f:
+    max_length = json.load(f)
+    
+def pad(x, length=None):
+    return pad_sequences(x, maxlen=length, padding='post')
+
+def translate_to_french(english_sentence):
+    english_sentence = english_sentence.lower()
+    english_sentence = re.sub(r'[.?!,]', '', english_sentence)
+    english_sentence = english_tokenizer.texts_to_sequences([english_sentence])
+    english_sentence = pad(english_sentence, max_length)
+    english_sentence = english_sentence.reshape((-1, max_length))
+    
+    french_sentence = model.predict(english_sentence)[0]
+    french_sentence = [np.argmax(word) for word in french_sentence]
+    french_sentence = french_tokenizer.sequences_to_texts([french_sentence])[0]
+    
+    return french_sentence
+
+def get_word_suggestions(word, vocab):
+    return difflib.get_close_matches(word, vocab, n=3, cutoff=0.6)
+
+def check_and_correct_sentence(sentence, vocab):
+    words = sentence.split()
+    incorrect_words.clear()
+    corrected_sentence = []
+    for word in words:
+        if word not in vocab:
+            suggestions = get_word_suggestions(word, vocab)
+            incorrect_words.append((word, suggestions))
+        else:
+            corrected_sentence.append(word)
+    
+    if incorrect_words:
+        message = f"Incorrect word(s) detected: {', '.join([w[0] for w in incorrect_words])}\n"
+        for word, suggestions in incorrect_words:
+            message += f"Suggestions for '{word}': {', '.join(suggestions) if suggestions else 'No suggestions available'}\n"
+        if len(incorrect_words) >= 1:
+            messagebox.showerror("Error", message)
+        return False
+    return True
+
+def translate_to_spanish(english_sentence):
+    if not check_and_correct_sentence(english_sentence, eng_vocab):
+        return ""
+    spanish_sentence = beam_search_decode(english_sentence)
+    return spanish_sentence.replace("[start]", "").replace("[end]", "").strip()
+
+# Function to handle translation request based on selected language
+def handle_translate():
+    selected_language = language_var.get()
+    english_sentence = text_input.get("1.0", "end-1c").strip()
+    
+    if not english_sentence:
+        messagebox.showwarning("Warning", "Please enter a sentence to translate.")
+        return
+    
+    if selected_language == "French":
+        translation = translate_to_french(english_sentence)
+    elif selected_language == "Spanish":
+        translation = translate_to_spanish(english_sentence)
+        
+    translation_output.delete("1.0", "end")
+    translation_output.insert("end", f"{selected_language} translation: {translation}")
+
+# Setting up the main window
+root = tk.Tk()
+root.title("Language Translator")
+root.geometry("550x600")
+
+# Font configuration
+font_style = "Times New Roman"
+font_size = 14
+
+# Frame for input
+input_frame = tk.Frame(root)
+input_frame.pack(pady=10)
+
+# Heading for input
+input_heading = tk.Label(input_frame, text="Enter the text to be translated", font=(font_style, font_size, 'bold'))
+input_heading.pack()
+# Text input for English sentence
+text_input = tk.Text(input_frame, height=5, width=50, font=(font_style, font_size))
+text_input.pack()
+
+# Language selection
+language_var = tk.StringVar()
+language_label = tk.Label(root, text="Select the language to translate to", font=(font_style, font_size, 'bold'))
+language_label.pack()
+language_select = ttk.Combobox(root, textvariable=language_var, values=["French", "Spanish"], font=(font_style, font_size), state="readonly")
+language_select.pack()
+
+# Submit button
+submit_button = ttk.Button(root, text="Translate", command=handle_translate)
+submit_button.pack(pady=10)
+
+# Frame for output
+output_frame = tk.Frame(root)
+output_frame.pack(pady=10)
+# Heading for output
+output_heading = tk.Label(output_frame, text="Translation: ", font=(font_style, font_size, 'bold'))
+output_heading.pack()
+
+# Text output for translations
+translation_output = tk.Text(output_frame, height=10, width=50, font=(font_style, font_size))
+translation_output.pack()
+
+# Running the application
+root.mainloop()

Task 2/sequence_length.json

@@ -0,0 +1 @@
+21

Task 2/spa_vectorization_config.json

@@ -0,0 +1 @@
+{"name": "text_vectorization_1", "trainable": true, "batch_input_shape": [null], "dtype": "string", "max_tokens": 15000, "split": "whitespace", "ngrams": null, "output_mode": "int", "output_sequence_length": 21, "pad_to_max_tokens": false, "sparse": false, "ragged": false, "vocabulary": null, "idf_weights": null}

Task 2/test_hindi_to_english.py

@@ -0,0 +1,57 @@
+import speech_recognition as sr
+from deep_translator import GoogleTranslator
+from datetime import datetime, time
+import pytz
+
+def is_within_operating_hours():
+    # Get current time in IST
+    ist = pytz.timezone('Asia/Kolkata')
+    current_time = datetime.now(ist).time()
+    # Define the operating time range
+    start_time = time(13, 0, 0)  # 6 PM IST
+    end_time = time(23, 59, 59)  # Midnight
+    return start_time <= current_time <= end_time
+
+def capture_audio():
+    recognizer = sr.Recognizer()
+    with sr.Microphone() as source:
+        print("Please speak now:")
+        audio = recognizer.listen(source)
+        try:
+            text = recognizer.recognize_google(audio)
+            print("You said: " + text)
+            return text
+        except sr.UnknownValueError:
+            print("Sorry, I did not understand the audio. Please repeat.")
+            return None
+        except sr.RequestError:
+            print("Network error. Please check your connection.")
+            return None
+
+def translate_text(text):
+    translator = GoogleTranslator(source='en', target='hi')
+    words = text.split()
+    translated_words = []
+    for word in words:
+        if word[0].upper() not in ['M', 'O']:
+            translated_word = translator.translate(word)
+            translated_words.append(translated_word)
+        else:
+            translated_words.append(word)
+    return ' '.join(translated_words)
+
+def main():
+    if not is_within_operating_hours():
+        print("Translation feature is available only after 6 PM IST.")
+        return
+
+    text = None
+    while text is None:
+        text = capture_audio()
+
+    if text:
+        translated_text = translate_text(text)
+        print("Translated text:", translated_text)
+
+if __name__ == "__main__":
+    main()

Task 2/transformer_model/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c57e5b1c49a163881bb486d7ab440406af67981fb4d43c1b293d4f3e8be60b6b
+size 58739

Task 2/transformer_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e90ad65260d2a5f6b86eb2222070bfff801829a65b959df096fdf5609f4979
+size 1305169

Task 2/transformer_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dee90376f3c6db9eac3b062c85fb1490b06871eaf8b078b2b312b0071e20033
+size 159724466