{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset, Audio\n",
    "from transformers import WhisperProcessor, WhisperForConditionalGeneration\n",
    "\n",
    "processor = WhisperProcessor.from_pretrained(\"openai/whisper-base\")\n",
    "\n",
    "common_voice = load_dataset(\"mozilla-foundation/common_voice_16_1\", \"zh-TW\", split=\"train\", streaming=False)\n",
    "common_voice = common_voice.cast_column(\"audio\", Audio(sampling_rate=processor.feature_extractor.sampling_rate))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "for i in common_voice:\n",
    "    print(i)\n",
    "    time.sleep(5)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}