detoxify and toxic
These are competitors: both independently solve the same Jigsaw Toxic Comment Classification task, with Unitary AI's detoxify being the more mature and widely-adopted solution (production API, active maintenance, higher adoption metrics) compared to Ostyakov's implementation.
About detoxify
unitaryai/detoxify
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
Provides three distinct model variants—`original`, `unbiased`, and `multilingual`—each optimized for different toxicity detection scenarios, with lightweight ALBERT-based alternatives for resource-constrained deployments. Leverages transformer-based architectures with bias-aware training on aggregated annotator judgments, supporting multi-label classification across toxicity subtypes (obscenity, threats, identity attacks, etc.) and identity mentions. Exposes predictions via a simple Python API returning per-category confidence scores and supports inference across seven languages with per-language performance metrics.
About toxic
PavelOstyakov/toxic
Toxic Comment Classification Challenge
Implements multi-label toxic comment classification using Keras with fastText embeddings (300d), processing six toxicity categories simultaneously. The pipeline combines NLTK preprocessing with scikit-learn utilities to train deep learning models that achieve competitive leaderboard performance on the Kaggle Jigsaw competition dataset.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work