[RapidVideOCR周边] RapidVideOCR高级教程（有python基础的小伙伴）

1. 安装使用VideoSubFinder软件

   • 下载地址：Windows & Linux (videosubfinder官网 / QQ群（706807542）共享文件) | Mac版
   • 使用教程：VideoSubFinder提取字幕关键帧教程
   • 最终生成的RGBImages和TXTImages目录一般会在软件安装目录下
   • ✧ 推荐用RGBImages目录中图像（感谢小伙伴dyphire在#21的反馈）

2. 安装rapid_videocr

   pip install rapid_videocr
   

3. 脚本运行：

   • Only OCR:

     from rapid_videocr import RapidVideOCR
     
     # RapidVideOCR有两个初始化参数
     # is_concat_rec: 是否用单张图识别，默认是False，也就是默认用单图识别
     # concat_batch: 叠图识别的图像张数，默认10，可自行调节
     # out_format: 输出格式选择，[srt, txt, all], 默认是 all
     # is_print_console: 是否打印结果，[0, 1], 默认是0，不打印
     extractor = RapidVideOCR(is_concat=False,
                                 out_format='all',
                                 is_print_console=False)
     
     # Windows端，需要这样写： rgb_dir = r'G:\ProgramFiles\_self\RapidVideOCR\test_files\RGBImages'
     # Linux / Mac 下面这样写
     rgb_dir = 'test_files/TXTImages'
     save_dir = 'result'
     extractor(rgb_dir, save_dir)
     

   • Extract + OCR:

     from rapid_videocr import RapidVideoSubFinderOCR
     
     vsf_exe = r"G:\ProgramFiles\VideoSubFinder_6.10_x64\Release_x64\VideoSubFinderWXW.exe"
     extractor = RapidVideoSubFinderOCR(vsf_exe_path=vsf_exe, is_concat_rec=True)
     
     # video_path can be directory path or video full path.
     video_path = 'test_files/tiny/2.mp4'
     save_dir = 'outputs'
     extractor(video_path, save_dir)
     

4. 命令行运行：

   • Usage:

     $ rapid_videocr -h
     usage: rapid_videocr [-h] [-vsf VSF_EXE_PATH] [-video_dir VIDEO_DIR] [-i IMG_DIR] [-s SAVE_DIR] [-o {srt,txt,all}] [-m {single,concat}] [-b CONCAT_BATCH] [-p {0,1}]
     
     options:
     -h, --help            show this help message and exit
     -vsf VSF_EXE_PATH, --vsf_exe_path VSF_EXE_PATH
                             The full path of VideoSubFinderWXW.exe.
     -video_dir VIDEO_DIR, --video_dir VIDEO_DIR
                             The full path of video or the path of video directory.
     -i IMG_DIR, --img_dir IMG_DIR
                             The full path of RGBImages or TXTImages.
     -s SAVE_DIR, --save_dir SAVE_DIR
                             The path of saving the recognition result. Default is "outputs" under the current directory.
     -o {srt,txt,all}, --out_format {srt,txt,all}
                             Output file format. Default is "all".
     -m {single,concat}, --mode {single,concat}
                             Which mode to run (concat recognition or single recognition). Default is "single".
     -b CONCAT_BATCH, --concat_batch CONCAT_BATCH
                             The batch of concating image nums in concat recognition mode. Default is 10.
     -p {0,1}, --print_console {0,1}
                             Whether to print the subtitle results to console. 1 means to print results to console. Default is 0.
     

   • Example:
     • Only OCR:

       $ rapid_videocr -i RGBImages
       

     • Extract + OCR:

       $ rapid_videocr -vsf G:\ProgramFiles\VideoSubFinder_6.10_x64\Release_x64\VideoSubFinderWXW.exe -video_dir G:\ProgramFiles\RapidVideOCR\test_files\tiny
       

5. 查看结果

   • 前往save_dir目录下即可查看结果。
   • 值得注意的是，如果想要让视频播放软件自动挂载srt文件，需要更改srt文件名字为视频文件名字，且放到同一目录下，亦或者手动指定加载。

PS: 详情参见RapidVideOCR