https://github.com/nata-vito/llm-video-description

https://github.com/nata-vito/llm-video-description

Last synced: 20 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/nata-vito/llm-video-description
• Owner: nata-vito
• Created: 2024-09-13T18:57:07.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-09-16T22:43:23.000Z (2 months ago)
• Last Synced: 2024-09-17T03:33:31.355Z (2 months ago)
• Language: Jupyter Notebook
• Size: 42 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Auto Video Description

Tool to help video description generation for multi purposes.

## How to Install:

```bash

# Clone repository

git clone 

cd llm-video-description

# Install the dependencies

sudo apt update && sudo apt install ffmpeg

pip install -r requirements.txt

# ollama serve

curl -fsSL https://ollama.com/install.sh | sh

# Install llama3.1 

ollama pull llama3.1

# Run llama3.1

ollama serve

# Run the script

python source/scripts/audio_to_text.py

```

## How to Use:

- 1 - Create the folder llm-video-description/source/audio/, llm-video-description/source/output/ and import your audio file to this new path

- 1.1 - Change the audio file name to transcription.mp3

- 2 - Run the commands in the root folder:

```bash

# Run the script

python source/scripts/audio_to_text.py

```

## How to fix it:

To:

```bash

bind: address already in use

```

Do:

```bash

systemctl stop ollama

ollama serve

```

## TODO:

- LMM Speech to text: DONE

- LLM to generate description: DONE

- Easy to use: ---