Metadata-Version: 2.4
Name: T5SummaryPratik
Version: 0.1.0
Summary: A complete text summarization pipeline using T5 with evaluation metrics
Home-page: https://github.com/yourusername/T5SummaryPratik
Author: Pratik
Author-email: your.email@example.com
Project-URL: Bug Reports, https://github.com/yourusername/T5SummaryPratik/issues
Project-URL: Source, https://github.com/yourusername/T5SummaryPratik
Keywords: text summarization,t5,nlp,machine learning
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing :: General
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: transformers
Requires-Dist: torch
Requires-Dist: evaluate
Requires-Dist: textstat
Requires-Dist: nltk
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# T5SummaryPratik

A powerful text summarization library using T5 transformer model with built-in evaluation metrics.

## Installation

```bash
pip install T5SummaryPratik
```

## Features

- Text summarization using T5 transformer model
- Multiple evaluation metrics:
  - ROUGE scores
  - Readability metrics
  - Text statistics
- Easy to use API
- Customizable parameters

## Quick Start

```python
from T5SummaryPratik import T5Summarizer

# Initialize the summarizer
summarizer = T5Summarizer()

# Example text
text = """
Your long text here that needs to be summarized.
This can be multiple paragraphs long.
"""

# Generate summary
summary = summarizer.summarize(text)
print(summary)

# Get summary with evaluation metrics
summary_with_metrics = summarizer.summarize_with_metrics(text)
print(f"Summary: {summary_with_metrics['summary']}")
print(f"ROUGE scores: {summary_with_metrics['metrics']['rouge']}")
print(f"Readability score: {summary_with_metrics['metrics']['readability']}")
```

## Advanced Usage

See [example_usage.py](example_usage.py) for more advanced usage examples.

## Requirements

- Python >= 3.8
- PyTorch
- Transformers
- NLTK
- Evaluate
- Textstat

## License

MIT License

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.
