Linux: Miniconda3-p圓8_4.11.0-Linux-x86_64.We extract subtitles from videos for different purposes. PS: can only run CLI version on Google Colab Getting Started with Source Code 1.
Provide your suggestions to improve this project in ISSUES Demo You can install CUDA and cuDNN to speed up the detection and recognition process and even get more accurate results. This program will automatically detect the subtitle area for you.
For Command Line Interface(CLI) version, you can escape the subtitle area setting. There is no online API call and you dont need to connect to the Internet service provider in order to get results. You don't need to do any preprocessing (e.g., binarization) and don't need to consider all aspects like subtitle fonts and size etc. Windows executable (might be slow when initial start): vse.exe accurate: no subtitle missing while low extraction speed. fast: high extraction speed while few subtitle missing ( Recommended). Multiple language support, you can extract the following subtitle languages: Simplified Chinese, English, Japanese, Korean, Traditional Chinese, French, German, Russian, Spanish, Portuguese, Italian. You can select multiple video files at one time and this tool can generate subtitles for each video. Remove duplicated subtitle line and generate srt file (by calculating text similarity). Filter non-subtitle text (e.g., Logo and watermark etc.). Converting graphic text into plain-text (using deep learning algorithms). Detect subtitle areas (i.e., coordinates) (as well as scene text if you want) (using deep learning algorithms). Detect and extract subtitle frames (using traditional graphic method). It includes the following implementations: Video-subtitle-extractor (vse) is a free, open-source tool which can help you rip the hard-coded subtitles from a video file and automatically generate srt files for each video.
0 kommentar(er)
