A dead-simple image search and image-text matching system for Bangla using CLIP (Contrastive Language–Image Pre-training)

---

Installation

• python >= 3.9
• pip install -r requirements.txt
• Download the model weights and place inside the models folder.

bangla-image-search

The model consists of an EfficientNet / ResNet image encoder and a BERT text encoder and was trained on multiple datasets from Bangla image-text domain. To run the app,

streamlit run app.py

---

Demo

Live Demo: HuggingFace Space

Training CLIP for Bangla

• Training Code: bangla-CLIP
• Article: medium