CHANGELOG.md

# Changelog - Speech Recognition Dataset

<!--
============================================================================
Speech Recognition Dataset - Changelog
============================================================================

Project: Speech Recognition Dataset
Website: https://rskworld.in
Founded by: Molla Samser
Designer & Tester: Rima Khatun
Email: help@rskworld.in
Support: support@rskworld.in
Phone: +91 93305 39277

============================================================================
COPYRIGHT NOTICE
============================================================================
© 2026 RSK World. All rights reserved.
This dataset is provided for educational and research purposes.

============================================================================
-->

## Version 1.0.0 (2026)

### Added
- ✅ Complete project structure with all folders and files
- ✅ Interactive demo page (index.html) with modern UI/UX
- ✅ Advanced features: preloader, custom cursor, theme toggle, search modal
- ✅ Browser Speech Synthesis for real text-to-speech
- ✅ Audio player with volume control
- ✅ Sample audio cards with play functionality
- ✅ Statistics visualization with Chart.js
- ✅ Code examples for Python, Librosa, TensorFlow, PyTorch
- ✅ Spectrogram visualization section
- ✅ FAQ section with accordion
- ✅ Newsletter subscription section
- ✅ Complete Python scripts for dataset loading, preprocessing, training
- ✅ Data augmentation scripts
- ✅ Transformer/Conformer model support
- ✅ Model evaluation scripts
- ✅ Jupyter notebook for data exploration
- ✅ 50 sample audio files generated
- ✅ Complete metadata.csv with 50 entries
- ✅ Complete transcripts.json with 50 entries
- ✅ Requirements.txt with all dependencies
- ✅ Complete documentation (README.md, PROJECT_SUMMARY.md)
- ✅ License file
- ✅ .gitignore with proper rules
- ✅ __init__.py for Python package structure
- ✅ .gitkeep files for empty directories

### Fixed
- ✅ Updated all copyright years from 2024 to 2026
- ✅ Fixed page refresh issue on anchor link clicks
- ✅ Fixed audio playback to use browser Speech Synthesis
- ✅ Fixed speech synthesis voice loading issue
- ✅ Fixed .gitignore copyright year
- ✅ Updated Open Graph image reference

### Improved
- ✅ Enhanced UI/UX with glassmorphism effects
- ✅ Added scroll reveal animations (AOS)
- ✅ Improved responsive design
- ✅ Better error handling in Python scripts
- ✅ Added developer information in all files
- ✅ Improved code organization and comments

### Technical Details
- **Frontend**: HTML5, CSS3, JavaScript (ES6+)
- **Backend**: Python 3.8+
- **Libraries**: TensorFlow, PyTorch, Librosa, NumPy, Pandas
- **UI Libraries**: Font Awesome, AOS, Chart.js
- **Browser Support**: Modern browsers with Speech Synthesis API

---

© 2026 RSK World. All rights reserved.