Video Subtitle Extractor Bot

A simple Telegram bot to extract hard-coded subtitle from videos using FFmpeg & Tesseract.

Note that the recognition accuracy depends on the subtitle font and its visibility.

Deploy to Heroku

Local Deploying

Make sure you have Tesseract and FFmpeg.

Clone the repo

git clone https://github.com/samadii/VidSubExtract-Bot

Go to this line and add the PATH where Tesseract is installed.
Also fill this path with the path of the tessdata folder.
Enter the directory
```
cd VidSubExtract-Bot
```
Install all requirements using pip.
```
pip3 install -r requirements.txt
```
Run the file
```
python3 main.py
```

Environment Variables

API_ID - Get this from my.telegram.org
API_HASH - Get this from my.telegram.org
BOT_TOKEN - Get this from @BotFather
SUBTITLE_LANG - Get this from list of ISO 639-2 language codes
USE_CROP - Set this to ANYTHING to enable crop mode(crop out subtitles area).

Devs:

@samadii