https://github.com/vortex2jm/video-summarizer
Audio extraction, transcription and summarization using AI
https://github.com/vortex2jm/video-summarizer
deepseek-v3 faster-whisper ffmpeg
Last synced: 6 months ago
JSON representation
Audio extraction, transcription and summarization using AI
- Host: GitHub
- URL: https://github.com/vortex2jm/video-summarizer
- Owner: vortex2jm
- Created: 2025-04-09T17:05:50.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-04-09T17:10:05.000Z (6 months ago)
- Last Synced: 2025-04-11T00:17:58.368Z (6 months ago)
- Topics: deepseek-v3, faster-whisper, ffmpeg
- Language: Python
- Homepage:
- Size: 2.93 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Blog text generator
- This script receives a video as input and follows the pipeline below:
1. Extracts the .mp3 audio from video with a 16k bit rate, 12KHz sample rate, and 1 channel;
2. Transcripts the audio with FasterWhisper model;
3. Uses DeepSeek to create a summary with the transcripted audio;
### Requirements
```bash
sudo apt install ffmpeg
```
```bash
pip install -r requirements.txt
```
### Usage
```bash
python3 main.py
```