# Devanagari-Characters-Image

**Repository Path**: hf-datasets/Devanagari-Characters-Image

## Basic Information

- **Project Name**: Devanagari-Characters-Image
- **Description**: Mirror of https://huggingface.co/datasets/Mayank022/Devanagari-Characters-Image
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-08-10
- **Last Updated**: 2025-08-10

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

---
dataset_name: Devanagari Characters Image Dataset
annotations_creators: [other]
language_creators: [found]
language: [hi, mr, sa]
task_categories:
  - image-classification
  - unconditional-image-generation

task_ids:
  - multi-class-image-classification


license: other
tags:
  - devanagari
  - hindi
  - diffusion
  - ocr
  - fonts
size_categories:
  - 10K<n<100K

---

#  Devanagari Characters Image Dataset

## Dataset Summary

The **Devanagari Characters Image Dataset** is a high-resolution dataset designed to support research and experimentation in generative modeling, specifically for the Hindi script. It includes images for:

- **Vowels (स्वर)**
- **Consonants (व्यंजन)**
- **Matra combinations (e.g., का, कि, की, कु)**
- **Hindi numerals (०-९)**


![image/gif](https://cdn-uploads.huggingface.co/production/uploads/666c3d6489e21df7d4a02805/vTze8X-7JXwz9wH5dtQbJ.gif)

The dataset was created to address the limitations of existing Devanagari datasets, which often suffer from low resolution (typically 32x32 pixels) and limited font variety. This dataset provides a more robust and scalable resource for training advanced generative models such as diffusion models.
But it can be used for some other problem statement as well.

---

## Use Cases

- Hindi character generation using diffusion models
- Full sentence-level generation and rendering
- OCR pretraining and benchmarking for Devanagari
- Font style transfer and augmentation
- High-resolution classification tasks

---

## Dataset Details

- **Characters Covered**: 80+ (including vowels, consonants, matra combinations, and numerals)
- **Font Variations**: 305 unique Devanagari Unicode fonts
- **Resolution**: 128x128 pixels (grayscale)
- **Images per Character**: ~305
- **Total Size**: ~24,000 images

Each character image is rendered programmatically using Unicode-compliant Devanagari fonts to ensure consistency and readability across styles.

---

## Character Coverage

The dataset includes:

### Vowels (स्वर)
`अ, आ, इ, ई, उ, ऊ, ऋ, ॠ, ऌ, ॡ, ए, ऐ, ओ, औ, अं, अः`

### Consonants (व्यंजन)
`क, ख, ग, घ, ङ, च, छ, ज, झ, ञ, ट, ठ, ड, ढ, ण, त, थ, द, ध, न, प, फ, ब, भ, म, य, र, ल, व, श, ष, स, ह, ळ, क्ष, त्र, ज्ञ`

### Matra Combinations (e.g.,)
`का, कि, की, कु, कू, कृ, के, कै, को, कौ, कं, कः`, `गा, गि, गु, गो`, etc.

### Hindi Numerals
`०, १, २, ३, ४, ५, ६, ७, ८, ९, १०`

---

## Motivation

While exploring the application of diffusion models for multilingual character generation, a key bottleneck was the lack of high-resolution and stylistically diverse datasets in Hindi. This dataset was created to fill that gap. It provides a clean, diverse, and high-resolution dataset suitable for generative tasks and deep learning experimentation.

---

## Limitations

- The dataset is synthetically generated using fonts and does not include handwritten data.
- Some fonts may render characters with minor stylistic irregularities, especially in matra combinations.