Add Data Augmentation Integration

## 🚀 Feature

Add transforms for data augmentation

**Motivation**

During training data augmentation are essential for better performances

The issue does not name any files, tests, or existing entry points. Start by locating NLPiper's transformation and preprocessing components, then clarify which augmentation techniques and interfaces are required. Done should mean the agreed transforms are integrated for training and covered by appropriate tests.

Written by the indexing model from the issue text.