{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline\n",
    "\n",
    "fill_mask = pipeline(\n",
    "    \"fill-mask\",\n",
    "    model=\"latin_BERT_final\",\n",
    "    tokenizer=\"latin_WP_tokenizer\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "False False False False False\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'score': 0.05949964374303818,\n",
       "  'token': 18,\n",
       "  'token_str': '.',\n",
       "  'sequence': 'roma in. est.'},\n",
       " {'score': 0.05125246196985245,\n",
       "  'token': 16,\n",
       "  'token_str': ',',\n",
       "  'sequence': 'roma in, est.'},\n",
       " {'score': 0.014972569420933723,\n",
       "  'token': 870,\n",
       "  'token_str': 'et',\n",
       "  'sequence': 'roma in et est.'},\n",
       " {'score': 0.009671307168900967,\n",
       "  'token': 879,\n",
       "  'token_str': '##que',\n",
       "  'sequence': 'roma inque est.'},\n",
       " {'score': 0.007990601472556591,\n",
       "  'token': 30,\n",
       "  'token_str': ':',\n",
       "  'sequence': 'roma in : est.'}]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fill_mask(\"Roma in [MASK] est.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "False False False False False\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'score': 0.05949964374303818,\n",
       "  'token': 18,\n",
       "  'token_str': '.',\n",
       "  'sequence': 'ubi est.?.'},\n",
       " {'score': 0.05125246196985245,\n",
       "  'token': 16,\n",
       "  'token_str': ',',\n",
       "  'sequence': 'ubi est,?.'},\n",
       " {'score': 0.014972569420933723,\n",
       "  'token': 870,\n",
       "  'token_str': 'et',\n",
       "  'sequence': 'ubi est et?.'},\n",
       " {'score': 0.009671302512288094,\n",
       "  'token': 879,\n",
       "  'token_str': '##que',\n",
       "  'sequence': 'ubi estque?.'},\n",
       " {'score': 0.007990599609911442,\n",
       "  'token': 30,\n",
       "  'token_str': ':',\n",
       "  'sequence': 'ubi est :?.'}]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fill_mask(\"Ubi est [MASK] ?.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "False False False False False\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'score': 0.05949964374303818,\n",
       "  'token': 18,\n",
       "  'token_str': '.',\n",
       "  'sequence': 'de honoratorum.'},\n",
       " {'score': 0.05125246196985245,\n",
       "  'token': 16,\n",
       "  'token_str': ',',\n",
       "  'sequence': 'de honoratorum,'},\n",
       " {'score': 0.014972569420933723,\n",
       "  'token': 870,\n",
       "  'token_str': 'et',\n",
       "  'sequence': 'de honoratorum et'},\n",
       " {'score': 0.009671302512288094,\n",
       "  'token': 879,\n",
       "  'token_str': '##que',\n",
       "  'sequence': 'de honoratorumque'},\n",
       " {'score': 0.007990601472556591,\n",
       "  'token': 30,\n",
       "  'token_str': ':',\n",
       "  'sequence': 'de honoratorum :'}]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# De honoratorum vehiculis\n",
    "fill_mask(\"De honoratorum [MASK]\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "bertenv",
   "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": "3.9.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}