Libraries & frameworks
TextAttack
QData/TextAttack
TextAttack is a Python framework for adversarial attacks, data augmentation, and model training in NLP, with reusable attack recipes, built-in models, and a command-line interface for research and robustness testing.
Topics
Related projects
datasets22.1kA Python library for one-line loading, streaming, and efficient preprocessing of large public datasets for model training and evaluation.
audiomentations2.3kAudiomentations is a Python library for audio data augmentation, offering composable transforms that help audio machine-learning models generalize beyond the lab.
synthcity693Synthcity is a Python library for generating and evaluating synthetic tabular data. It offers a plugin architecture with many generative models and built-in metrics for privacy, fairness, fidelity, and data augmentation.
best-of-ml-python23.9kA curated, ranked list of 920 awesome machine learning Python libraries across 34 categories, updated weekly.
FinGPT21.6kAn open-source financial LLM project publishing fine-tuned model weights, datasets, and robo-advisor demos for finance tasks.
ML-NLP17.8kA curated Chinese study collection of ML and NLP interview notes with code examples.