Hate Speech Python Packages

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.

lexicont

Lightweight LLM agent for text moderation with deterministic pipeline: profanity rules → ML → LLM. Production-grade, YAML configurable. Uses glin-profanity + rapidfuzz + detoxify with Qwen LLM agent (llamacpp/Ollama) + RAG. Early-stop logic. Pure Python, CLI/API/SDK.

toxicity

Deep learning classifier of russian toxic comments

honest

...

napolab

The Natural Portuguese Language Benchmark (Napolab). Stay up to date with the latest advancements in Portuguese language models and their performance across carefully curated Portuguese language tasks.