sanjifr3/Narrator

An image and video description generator using an CNN-RNN based architecture.

23
/ 100
Experimental

Integrates with Amazon Polly for text-to-speech synthesis and PySceneDetect for automatic video scene segmentation, enabling accessibility-focused description generation. Implements separate PyTorch models trained on COCO 2014 (image) and MSR-VTT (video) datasets using ResNet/VGG encoders paired with LSTM/GRU decoders, with optional beam search decoding. Deployable as both a Flask web service on AWS and a standalone Python API for flexible integration workflows.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 7 / 25

How are scores calculated?

Stars

25

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sanjifr3/Narrator"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.