{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "7b5f7142",
   "metadata": {},
   "outputs": [],
   "source": [
    "import transformers\n",
    "from datasets import load_dataset\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4ad6422f",
   "metadata": {},
   "outputs": [],
   "source": [
    "username = \"Plim\"  # change to your username\n",
    "target_lang = \"fr\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "37b2c1d6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f230feb459c441a9a11e53b867e8914a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/2.60k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a4a8fa35d48f4a6db8072baed6b2389b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/29.6k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using custom data configuration en-fr-lang1=en,lang2=fr\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading and preparing dataset europarl_bilingual/en-fr (download: 278.07 MiB, generated: 643.66 MiB, post-processed: Unknown size, total: 921.72 MiB) to /workspace/.cache/huggingface/datasets/europarl_bilingual/en-fr-lang1=en,lang2=fr/8.0.0/2ab0200e7729616bfd4a4df6bfb29b31746ceb5a59f8c75c02ca35e1ebead950...\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "aa00b5d6dc154449861dddcf9f0d2fc8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/142M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "563096fc78454333b5ae23e87a7e3469",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/140M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "eba05e5151b34505b9a43e383cb6cfe0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/9.30M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dataset europarl_bilingual downloaded and prepared to /workspace/.cache/huggingface/datasets/europarl_bilingual/en-fr-lang1=en,lang2=fr/8.0.0/2ab0200e7729616bfd4a4df6bfb29b31746ceb5a59f8c75c02ca35e1ebead950. Subsequent calls will reuse this data.\n"
     ]
    }
   ],
   "source": [
    "dataset = load_dataset(\"europarl_bilingual\", lang1=\"en\", lang2=target_lang, split=\"train\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "81259294",
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_text(batch):\n",
    "    target_lang = \"fr\"\n",
    "    chars_to_ignore_regex = '[^a-zàâäçéèêëîïôöùûüÿ\\'’ ]'\n",
    "    text = batch[\"translation\"][target_lang]\n",
    "    batch[\"text\"] = re.sub(chars_to_ignore_regex, \"\", text.lower()).replace('’', \"'\")\n",
    "    return batch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "2dec7b80",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "00d998de52544f6c8750c53bc0c85d66",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "0ex [00:00, ?ex/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset = dataset.map(extract_text, remove_columns=dataset.column_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c6feaf74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "461a219cdb6d42b2b890ec028c336e7f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset.push_to_hub(f\"{target_lang}_corpora_parliament_processed\", split=\"train\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b0e6ae25",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"text.txt\", \"w\") as file:\n",
    "    file.write(\" \".join(dataset[\"text\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f95596a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"5gram.arpa\", \"r\") as read_file, open(\"5gram_correct.arpa\", \"w\") as write_file:\n",
    "    has_added_eos = False\n",
    "    for line in read_file:\n",
    "        if not has_added_eos and \"ngram 1=\" in line:\n",
    "            count=line.strip().split(\"=\")[-1]\n",
    "            write_file.write(line.replace(f\"{count}\", f\"{int(count)+1}\"))\n",
    "        elif not has_added_eos and \"<s>\" in line:\n",
    "            write_file.write(line)\n",
    "            write_file.write(line.replace(\"<s>\", \"</s>\"))\n",
    "            has_added_eos = True\n",
    "        else:\n",
    "            write_file.write(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f6489f25",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "file ./config.json not found\n"
     ]
    },
    {
     "ename": "OSError",
     "evalue": "Can't load config for './'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './' is the correct path to a directory containing a config.json file",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/configuration_utils.py:585\u001b[0m, in \u001b[0;36mPretrainedConfig._get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    583\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    584\u001b[0m     \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 585\u001b[0m     resolved_config_file \u001b[38;5;241m=\u001b[39m \u001b[43mcached_path\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    586\u001b[0m \u001b[43m        \u001b[49m\u001b[43mconfig_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    587\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    588\u001b[0m \u001b[43m        \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    589\u001b[0m \u001b[43m        \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    590\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    591\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    592\u001b[0m \u001b[43m        \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_auth_token\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    593\u001b[0m \u001b[43m        \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    594\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    596\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RepositoryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m err:\n",
      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/file_utils.py:1861\u001b[0m, in \u001b[0;36mcached_path\u001b[0;34m(url_or_filename, cache_dir, force_download, proxies, resume_download, user_agent, extract_compressed_file, force_extract, use_auth_token, local_files_only)\u001b[0m\n\u001b[1;32m   1859\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m urlparse(url_or_filename)\u001b[38;5;241m.\u001b[39mscheme \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m   1860\u001b[0m     \u001b[38;5;66;03m# File, but it doesn't exist.\u001b[39;00m\n\u001b[0;32m-> 1861\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfile \u001b[39m\u001b[38;5;132;01m{\u001b[39;00murl_or_filename\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m not found\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m   1862\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1863\u001b[0m     \u001b[38;5;66;03m# Something unknown\u001b[39;00m\n",
      "\u001b[0;31mOSError\u001b[0m: file ./config.json not found",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
      "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoProcessor\n\u001b[0;32m----> 3\u001b[0m processor \u001b[38;5;241m=\u001b[39m \u001b[43mAutoProcessor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m./\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/models/auto/processing_auto.py:178\u001b[0m, in \u001b[0;36mAutoProcessor.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    176\u001b[0m \u001b[38;5;66;03m# Otherwise, load config, if it can be loaded.\u001b[39;00m\n\u001b[1;32m    177\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(config, PretrainedConfig):\n\u001b[0;32m--> 178\u001b[0m     config \u001b[38;5;241m=\u001b[39m \u001b[43mAutoConfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    180\u001b[0m model_type \u001b[38;5;241m=\u001b[39m config_class_to_model_type(\u001b[38;5;28mtype\u001b[39m(config)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n\u001b[1;32m    182\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(config, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprocessor_class\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m) \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/models/auto/configuration_auto.py:617\u001b[0m, in \u001b[0;36mAutoConfig.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    615\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname_or_path\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m pretrained_model_name_or_path\n\u001b[1;32m    616\u001b[0m trust_remote_code \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtrust_remote_code\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m--> 617\u001b[0m config_dict, _ \u001b[38;5;241m=\u001b[39m \u001b[43mPretrainedConfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_config_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    618\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mauto_map\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAutoConfig\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mauto_map\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[1;32m    619\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m trust_remote_code:\n",
      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/configuration_utils.py:537\u001b[0m, in \u001b[0;36mPretrainedConfig.get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    535\u001b[0m original_kwargs \u001b[38;5;241m=\u001b[39m copy\u001b[38;5;241m.\u001b[39mdeepcopy(kwargs)\n\u001b[1;32m    536\u001b[0m \u001b[38;5;66;03m# Get config dict associated with the base config file\u001b[39;00m\n\u001b[0;32m--> 537\u001b[0m config_dict, kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_config_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    539\u001b[0m \u001b[38;5;66;03m# That config file may point us toward another config file to use.\u001b[39;00m\n\u001b[1;32m    540\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mconfiguration_files\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict:\n",
      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/configuration_utils.py:626\u001b[0m, in \u001b[0;36mPretrainedConfig._get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    624\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m    625\u001b[0m     logger\u001b[38;5;241m.\u001b[39merror(err)\n\u001b[0;32m--> 626\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m    627\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load config for \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. If you were trying to load it from \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    628\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, make sure you don\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have a local directory with the same name. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    629\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOtherwise, make sure \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is the correct path to a directory \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    630\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontaining a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfiguration_file\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m file\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    631\u001b[0m     )\n\u001b[1;32m    633\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    634\u001b[0m     \u001b[38;5;66;03m# Load config dict\u001b[39;00m\n\u001b[1;32m    635\u001b[0m     config_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_dict_from_json_file(resolved_config_file)\n",
      "\u001b[0;31mOSError\u001b[0m: Can't load config for './'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './' is the correct path to a directory containing a config.json file"
     ]
    }
   ],
   "source": [
    "from transformers import AutoProcessor\n",
    "\n",
    "processor = AutoProcessor.from_pretrained(\"./\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ab24f645",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}