whisper-yt-search-get-transcriptions.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e58ca384-1f49-4565-ae1b-67c046dc38a8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Dataset({\n",
       "    features: ['title', 'visibility', 'published', 'url', 'id', 'text', 'start', 'end'],\n",
       "    num_rows: 27214\n",
       "})"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from datasets import load_dataset  # !pip install datasets\n",
    "\n",
    "data = load_dataset(\n",
    "    \"jamescalam/youtube-transcriptions\",\n",
    "    split=\"train\",\n",
    "    revision=\"8dca835\"\n",
    ")\n",
    "data"
   ]
  }
 ],
 "metadata": {
  "environment": {
   "kernel": "python3",
   "name": "common-cu110.m95",
   "type": "gcloud",
   "uri": "gcr.io/deeplearning-platform-release/base-cu110:m95"
  },
  "kernelspec": {
   "display_name": "Python 3.9.12 ('ml')",
   "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": "3.9.12"
  },
  "vscode": {
   "interpreter": {
    "hash": "b8e7999f96e1b425e2d542f21b571f5a4be3e97158b0b46ea1b2500df63956ce"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}