tokenizer_build.ipynb

{
 "cells": [
  {
   "source": [
    "Get a list of paths to each file in our *oscar_it* directory."
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "paths = [str(x) for x in Path('../../data/text/oscar_it').glob('**/*.txt')]"
   ]
  },
  {
   "source": [
    "Now we move onto training the tokenizer. We use a byte-level Byte-pair encoding (BPE) tokenizer. This allows us to build the vocabulary from an alphabet of single bytes, meaning all words will be decomposable into tokens."
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tokenizers import ByteLevelBPETokenizer\n",
    "\n",
    "tokenizer = ByteLevelBPETokenizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "tokenizer.train(files=paths[:5], vocab_size=30_522, min_frequency=2,\n",
    "                special_tokens=['<s>', '<pad>', '</s>', '<unk>', '<mask>'])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "ML",
   "language": "python",
   "name": "ml"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}