You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

BengaliSynth Models

Trained PyTorch checkpoints (.pt) for Bengali handwriting style extraction and text synthesis.

Checkpoints Included

  • font_generator_pilot_grapheme_complete.pt
  • attn_locator.pt

Descriptions:

  • font_generator_pilot_grapheme_complete.pt: Grapheme-conditioned U-Net generator with embedded GraphemeStyle encoder.
  • attn_locator.pt: 2D attention reader that locates Bengali graphemes and computes confidence scores.

Usage in BengaliSynth_Streamlit

Update MODELS_REPO_ID in BengaliSynth_Streamlit/src/synth/config.py:

MODELS_REPO_ID = "Partha11/bengalisynth-models"
MODELS_REPO_URL = f"https://huggingface.co/{MODELS_REPO_ID}/resolve/main"

The Streamlit app will automatically pull these .pt checkpoints on bootup.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support