https://github.com/botbahlul/vosk_autosrt
A python script COMMAND LINE utility to AUTO GENERATE SUBTITLE FILE (using free Vosk Speech Recognition API) and TRANSLATED SUBTITLE FILE (using unofficial online Google Translate API) for any video or audio file
https://github.com/botbahlul/vosk_autosrt
auto-caption auto-subtitle caption ffmpeg google-translate-api python speech-recognition speechrecognition subtitle voice-recognition voicerecognition vosk
Last synced: 7 months ago
JSON representation
A python script COMMAND LINE utility to AUTO GENERATE SUBTITLE FILE (using free Vosk Speech Recognition API) and TRANSLATED SUBTITLE FILE (using unofficial online Google Translate API) for any video or audio file
- Host: GitHub
- URL: https://github.com/botbahlul/vosk_autosrt
- Owner: botbahlul
- License: mit
- Created: 2023-05-31T20:08:38.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2024-05-05T17:05:23.000Z (about 2 years ago)
- Last Synced: 2025-03-25T13:45:39.504Z (about 1 year ago)
- Topics: auto-caption, auto-subtitle, caption, ffmpeg, google-translate-api, python, speech-recognition, speechrecognition, subtitle, voice-recognition, voicerecognition, vosk
- Language: Python
- Homepage:
- Size: 20.1 MB
- Stars: 9
- Watchers: 2
- Forks: 2
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# vosk_autosrt 
### Auto-generated subtitles for any video/audio files
vosk_autosrt is a simple command line tool made with python to auto generate subtitle/closed caption file for any video or audio file using VOSK API and translate it automaticly for free using unofficial Google Translate API.
### Installation
If you don't have python on your Windows system you can try the compiled version from this git release assets
https://github.com/botbahlul/vosk_autosrt/releases
Just extract those ffmpeg.exe, ffprobe.exe, and vosk_autosrt.exe into a folder that has been added to PATH ENVIRONMENT for example in C:\Windows\system32
If it doesn't run well then you need to install python on your Windows system
You can get latest version of ffmpeg and ffprobe from https://www.ffmpeg.org/
In Linux you have to install this script with python (version minimal 3.8) and install ffmpeg with your linux package manager for example in debian based linux distribution you can type :
```
apt update
apt install -y ffmpeg
```
To install this vosk_autosrt, just type :
```
pip install vosk_autosrt
```
When you run this app for the very first time it may takes some times to download vosk language model, you can check those downloaded models in "/home/username/.cache/vosk" (if you're on Linux) and "C:\\Users\\Username\\.cache\vosk\\" (if you're on Windows).
You can always download those small models manually from https://alphacephei.com/vosk/models then extract them to that used folder.
DON'T FORGET TO CHANGE YOUR CONSOLE (COMMAND PROMPT WINDOW) CODE PAGE TO 65001 (UTF-8)!
```
To change the codepage for the console, do the following:
Start -> Run -> regedit
Go to [HKEY_LOCAL_MACHINE\Software\Microsoft\Command Processor\Autorun]
Change the value to @chcp 65001>nul
If Autorun is not present, you can add a New String
```
You can try to compile that vosk_autosrt.py script in win/linux/mac folder into a single executable file with that mypyinstaller.bat (on windows)/mypyinstaller.sh (on linux/macos):
```
pip install pyinstaller
mypyinstaller.bat
```
The executable compiled file will be placed by pyinstaller into dist subfolder of your current working folder, so you can just rename and put that compiled file into a folder that has been added to your PATH ENVIRONTMENT so you can execute it from anywhere
I was succesfuly compiled it in Windows 10 with pyinstaller-5.1 and Pyhton-3.10.4, and python-3.8.12 in Debian 9
Another alternative way to install this script with python is by cloning this git (or downloading this git as zip then extract it into a folder), and then just type :
```
pip install wheel
cd vosk_autosrt
python setup.py bdist_wheel
```
Then check the name of the whl file created in dist folder. In case the filename is vosk_autosrt-0.0.2-cp310-cp310-win_amd64.whl then you can install that whl file with pip :
```
cd dist
pip install vosk_autosrt-0.0.2-cp310-cp310-win_amd64.whl
```
You can also install this script (or any pip package) in ANDROID DEVICES via PYTHON package in TERMUX APP
https://github.com/termux/termux-app/releases/tag/v0.118.0
Choose the right apk for your device, install it, then open it
Type these commands to get python, pip, this vosk_autosrt, (and any other pip packages) :
```
termux-setup-storage
pkg update -y
pkg install -y python
pkg install -y ffmpeg
pip install vosk_autosrt
```
### Simple usage example
```
vosk_autosrt --list-src-languages
vosk_autosrt -S zh -D en "Episode 1.mp4"
```
If you don't need translations just type :
```
vosk_autosrt -S zh "Episode 1.mp4"
```
### Usage
```
usage: vosk_autosrt [-h] [-S SRC_LANGUAGE] [-D DST_LANGUAGE] [-lls] [-lld] [-F FORMAT] [-lf] [-C CONCURRENCY] [-es EMBED_SRC]
[-ed EMBED_DST] [-fr FORCE_RECOGNIZE] [-v]
[source_path ...]
positional arguments:
source_path Path to the video or audio files to generate subtitles files (use wildcard for multiple files or separate
them with a space character e.g. "file 1.mp4" "file 2.mp4")
options:
-h, --help show this help message and exit
-S SRC_LANGUAGE, --src-language SRC_LANGUAGE
Language code of the audio language spoken in video/audio source_path
-D DST_LANGUAGE, --dst-language DST_LANGUAGE
Desired translation language code for the subtitles
-lls, --list-src-languages
List all available source languages (vosk supported languages)
-lld, --list-dst-languages
List all available destination languages (google translate supported languages)
-F FORMAT, --format FORMAT
Desired subtitle format
-lf, --list-formats List all supported subtitle formats
-C CONCURRENCY, --concurrency CONCURRENCY
Number of concurrent translate API requests to make
-es EMBED_SRC, --embed-src EMBED_SRC
Boolean value (True or False) for embedding original language subtitle file into media file
-ed EMBED_DST, --embed-dst EMBED_DST
Boolean value (True or False) for embedding translated subtitle file into media file
-fr FORCE_RECOGNIZE, --force-recognize FORCE_RECOGNIZE
Boolean value (True or False) for re-recognize media file event if it's already has subtitles stream
-v, --version show program's version number and exit
```
### License
MIT
Check my other SPEECH RECOGNITIION + TRANSLATE PROJECTS https://github.com/botbahlul?tab=repositories
Buy me coffee : https://sociabuzz.com/botbahlul/tribe