whisper.ipynb

whisper.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "private_outputs": true,
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyPTN4AH8zHqNhbz9GoCD0SN",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/kwea123/e76cf754c8e2bd65576720505a36a899/whisper.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "NYwreAggjMRu"
      },
      "outputs": [],
      "source": [
        "# install whisper\n",
        "!pip install git+https://github.com/openai/whisper.git"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# mount drive\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive/', force_remount=True)"
      ],
      "metadata": {
        "id": "ixdvyG9Fnlpr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import glob\n",
        "\n",
        "use_drive = True # 是否用google drive(如果是上傳到這裡，設為\"False\"(去掉引號))\n",
        "folder = 'kouhaku2021' # 如果使用google drive，指定包含影片的資料夾(可包含多個影片)，須為MyDrive下的相對路徑\n",
        "                        # 如果是上傳檔案則不用修改\n",
        "language = 'Chinese' # 影片語言\n",
        "translate = False # 是否將字幕翻譯成英文 (如果要翻譯，設為\"True\"(去掉引號))\n",
        "\n",
        "if use_drive:\n",
        "  vids = glob.glob(os.path.join('/content/drive/MyDrive', folder, '*.mp4'))\n",
        "  out_dir = os.path.join('/content/drive/MyDrive', folder, 'subtitles')\n",
        "else:\n",
        "  vids = glob.glob('./*.mp4')\n",
        "  out_dir = './subtitles'\n",
        "for vid in vids:\n",
        "  print(f'處理 {vid} 中...')\n",
        "  cmd = f'whisper \"{vid}\" --language {language} \\\n",
        "      --model medium --output_dir {out_dir} --verbose False \\\n",
        "      --logprob_threshold None --no_speech_threshold 0.01'\n",
        "  if translate: cmd += ' --task translate'\n",
        "  os.system(cmd)"
      ],
      "metadata": {
        "id": "Lm7H6i7Vkn46"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "_le-Ud7dXmKg"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}