{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install datasets\n",
    "# !huggingface-cli login"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from datasets import load_dataset\n",
    "# load_dataset(\"balochiml/balochi-language-data\", data_dir=\"data\", cache_dir=\"../data\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4294"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "def get_txt_file_paths(directory):\n",
    "    txt_file_paths = []\n",
    "    for root, dirs, files in os.walk(directory):\n",
    "        for file in files:\n",
    "            if file.endswith(\".txt\"):\n",
    "                file_path = os.path.join(root, file)\n",
    "                txt_file_paths.append(file_path)\n",
    "    return txt_file_paths\n",
    "\n",
    "# Replace \"directory_path\" with the actual path of the directory you want to search\n",
    "directory_path = \"../data/raw_text\"\n",
    "txt_paths = get_txt_file_paths(directory_path)\n",
    "\n",
    "len(txt_paths)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "balochi",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.11"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}