Hate Speech Detection Transformer Models

Tools and models for identifying, classifying, and mitigating hate speech, offensive language, and toxic content in text. Does NOT include general sentiment analysis, stance detection, or content moderation for non-hateful policy violations.

There are 54 hate speech detection models tracked. The highest-rated is StyrbjornKall/TRIDENT at 39/100 with 16 stars.

Get all 54 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=hate-speech-detection&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	StyrbjornKall/TRIDENT A collection of transformer-based models and developmental scripts presented...	39	Emerging	16	Jupyter Notebook
2	Nithin-Holla/meme_challenge Repository containing code from team Kingsterdam for the Hateful Memes Challenge	39	Emerging	23	Python
3	viddexa/moderators One package to moderate them all	38	Emerging	5	Python
4	jaygala24/fed-hate-speech The official code repository for the paper titled "A Federated Approach for...	34	Emerging	10	Python
5	richouzo/hate-speech-detection-survey Trained Neural Networks (LSTM, HybridCNN/LSTM, PyramidCNN, Transformers,...	33	Emerging	21	Jupyter Notebook
6	MusadiqPasha/Turkish-Hate-Speech-Classification-Explanation Classify, explain, and rewrite Turkish hate speech tweets using BERT, SHAP,...	32	Emerging	3	Jupyter Notebook
7	ilias-ant/toxic-spans-detection An attempt at SemEval 2021 Task 5: Toxic Spans Detection.	31	Emerging	4	Jupyter Notebook
8	avrtt/telegram-content-moderator NLP/ViT-driven bot for detection & moredation of inappropriate content in...	30	Emerging	2	Python
9	iqbal-sk/Detecting-Persuasion-Techniques-in-Memes Hierarchical, multilingual, multimodal detection of persuasion techniques in...	30	Emerging	2	Jupyter Notebook
10	GU-DataLab/stance-detection-KE-MLM Official resource of the paper "Knowledge Enhanced Masked Language Model for...	29	Experimental	39	Python
11	nikhil6041/OLI-and-Meme-Classification Author's implementation of the paper...	27	Experimental	6	Jupyter Notebook
12	cvcio/rtaa-classifier Comments & Twitter accounts gRPC classification service.	26	Experimental	5	Python
13	jdleo/tinysafe-1 71M parameter safety classifier (DeBERTa-v3-xsmall). Dual-head: binary...	23	Experimental	2	Python
14	eftekhar-hossain/CUET_NLP-EACL_2021 This repository contains the system description and the codes that we...	23	Experimental	1	Jupyter Notebook
15	TimeLordRaps/satisfiable-ai Verified training data for frontier AI. Every sample passes a SAT gate....	22	Experimental	1	Python
16	jdleo/tinysafe-2 141M param safety model (not much better than v1, but a great learning)	22	Experimental	1	Python
17	pkdubey/content_moderation An AI-powered content moderation system using Python and Hugging Face...	22	Experimental	1	Python
18	chuachinhon/transformers_state_trolls_cch Detect state trolls on Twitter using Transformers + Comparison of results...	22	Experimental	2	Jupyter Notebook
19	mathildeoutters/Detect-patronizing-language Participation to SemEval-2022 Task4 - Patronizing and Condescending Language...	21	Experimental	1	Jupyter Notebook
20	AditiBagora/Hasoc2021CodeMix HASOC2021: Subtask 2 a) Codemix Challenge; Contains baselines and...	21	Experimental	1	Jupyter Notebook
21	premiouhxu4525/tinysafe-2 Classify text as safe or unsafe using a 141M parameter DeBERTa-v3 model with...	21	Experimental	—	Python
22	YukiFujimatsu/Personalized-Flaming-Prediction Implementation of personalized real-time flaming risk prediction model (IIAI...	21	Experimental	—	Jupyter Notebook
23	ArunavaKumar/offenseval-nlp Transformer-based offensive language detection using DistilBERT embeddings,...	21	Experimental	—	Jupyter Notebook
24	KvaytG/ru-toxicity-detector A simple toxicity detector.	21	Experimental	—	Python
25	shruti-sivakumar/Multimodal-Hateful-Memes-Detection Multimodal deep learning pipeline for hateful meme detection using ResNet50...	21	Experimental	—	Jupyter Notebook
26	nayanpreet/AI-Powered-Toxic-Comment-Detection-and-Moderation-System Transformer-based multi-label toxicity classifier with GenAI-assisted...	21	Experimental	—	Jupyter Notebook
27	minuva/fast-nlp-text-toxicity Fast text toxicity classification model	19	Experimental	4	Python
28	training-datalab/gold-standard-toxicity Gold Standard for Toxicity and Incivility Project	19	Experimental	3	R
29	Damarcreative/secure-upload Remove adult content in discord channels better with Artificial Intelligence.	19	Experimental	4	Python
30	hiyouga/Toxic_Detection BUAA SCSE Autumn 2021 Machine Learning Group Homework	19	Experimental	3	Python
31	muzmax/MSTAR_feature_extraction General Feature Extraction in SAR Target Classification: A Contrastive...	18	Experimental	2	Python
32	devroopsaha744/HateSpeechDetect-text In this project, I focused on benchmarking various machine learning models,...	17	Experimental	1	Jupyter Notebook
33	HumasFurquan/Hate-Speech-Detection-2.0 End-to-end hate speech detection system using Transformer-based NLP models,...	17	Experimental	—	Python
34	StyrbjornKall/TRIDENT_application Source code for the web application associated with "Transformers enable...	13	Experimental	3	Python
35	Brahmendra-Ramoju/TrustLayer_AI AI-powered content moderation API with toxicity detection and trust scoring...	13	Experimental	—	Python
36	Kirti-Vatsh/NLP---Toxic-Comment-Classification Classifying toxic comments using NLP, machine learning, and deep learning....	13	Experimental	—	Jupyter Notebook
37	Fabio295/tinysafe-1 Detect harmful content with a 71M-parameter safety classifier using...	13	Experimental	—	—
38	yellatp/detoxify-telugu A Fine-Tuned BERT-Based Language Model for Hate Speech Detection in Telugu & Tenglish	13	Experimental	—	Python
39	jaychampaneri14/content-moderator Multi-label content moderation for text and images	13	Experimental	—	Python
40	lopezrbn/kaggle_toxicity_challenge Multi-label toxic-comment classifier (DeBERTa v3, Kaggle Jigsaw Challenge) —...	13	Experimental	—	Jupyter Notebook
41	Bhawnakapri/DeepSignal-AI-Safety-Engine Transformer-based AI Safety Intelligence System for multi-label...	13	Experimental	—	Jupyter Notebook
42	kanincityy/misogyny_detection_transformers Building an Effective Misogyny Detection Classifier for Low-Resource Languages	13	Experimental	—	—
43	rafelps/HLE-UPC-SemEval-2021-ToxicSpansDetection HLE-UPC at SemEval-2021 Task 5: Toxic Spans Detection	12	Experimental	8	Python
44	Mussabat/HateSpeech-EACL-2024 This repository contains the system description and the codes that we...	12	Experimental	6	Jupyter Notebook
45	MagixIsAvailable/nlp_toxic_language A Real-Time AI Safety Filter that detects toxic speech from live audio using...	12	Experimental	1	Jupyter Notebook
46	yaekobB/Toxic-Comment-Classification Multi-label toxic comment classification using DistilBERT with explainable...	12	Experimental	1	Jupyter Notebook
47	karish-grover/Humor-Analysis-using-Ensembles-of-Simple-Transformers This paper describes Humor Analysis using Ensembles of Simple Transformers,...	12	Experimental	7	Jupyter Notebook
48	imdiptanu/MAD MAD: A Multi-task Aggression Detection Framework	11	Experimental	—	Python
49	rkeerthikant/proposed-model-for-trolls-detection Fine tuning DistilBERT, BERT-medium-uncased, T5-Small, MobileBERT for...	11	Experimental	—	Jupyter Notebook
50	Anshumaan-Chauhan02/HumanVsAI-Sarcasm-Detection Large Language Model performing a binary classification task of detecting...	11	Experimental	—	Jupyter Notebook
51	pavel-kalmykov/stance-detection-for-spanish-and-catalan Transformers applied to Stance Detection for Spanish and Catalan languages	11	Experimental	—	Jupyter Notebook
52	romsto/Inappropriate-Language-Classifier Online video games need a better system to detect inappropriate language in...	11	Experimental	4	Jupyter Notebook
53	neil-ab/contextual-hatespeech-detection A contextual (BERT-based) hate speech detection model	10	Experimental	2	Jupyter Notebook
54	rajendranu4/stance-detection Exploration of Contrastive Learning Strategies toward more Robust Stance Detection	10	Experimental	2	Jupyter Notebook

Comparisons in this category

tinysafe-1 and tinysafe-2 (23 vs 22)