Metadata-Version: 2.4
Name: indovse
Version: 0.1.4
Summary: Indonesian Video Salient Entity Detection
Author: galihkjaya
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: openai-whisper
Requires-Dist: transformers>=4.40
Requires-Dist: torch>=2.0
Requires-Dist: scikit-learn>=1.4
Requires-Dist: joblib
Requires-Dist: huggingface_hub
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: ffmpeg-python
Requires-Dist: yt-dlp
Requires-Dist: pypdf
Dynamic: author
Dynamic: description
Dynamic: description-content-type
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# IndoVSE

IndoVSE is a Python package for extracting salient named entities from Indonesian videos.

## Requirements

You must have `ffmpeg` installed on your system (not via pip).

- **Ubuntu/Debian:** `sudo apt install ffmpeg`
- **MacOS:** `brew install ffmpeg`
- **Windows:** Download from official ffmpeg website and add it to your system PATH.

## Installation

```bash
pip install indovse
```

_(atau instal dari source: `pip install -e .` di dalam folder ini)_

## Usage

```python
from indovse import predict_vid, predict_yt

# Models are downloaded and loaded during module import
# GPU is highly recommended for Whisper and BERT inference
result = predict_vid("video.mp4", top_k=5)

# YouTube URLs are also supported
yt_result = predict_yt("https://www.youtube.com/watch?v=example", top_k=5)

# Output is a dict with 'salient_entities' and 'entity_timeline'
print(result["salient_entities"])
```
