This BERT-based model (MuRIL) is trained to perform text classification for abusive content detection across multiple Indian languages. It is published by the Hate-speech-CNERG group and is available for inference using the Transformers library on Hugging Face.
Indic Abusive allInOne MuRIL sits in PulseGate's Other AI category. It focuses on identifying abusive or hateful content across multiple Indic languages. It is built as an open-source project for researchers and content moderation teams. Indic Abusive allInOne MuRIL is open source under the MIT license. Indic Abusive allInOne MuRIL is available on the web and API.
Hate-speech-CNERG builds and maintains Indic Abusive allInOne MuRIL, and it first shipped in 2022. Development happens publicly on GitHub with 10 stars. Among its 3 catalogued features are Text Classification, multilingual, and Abuse Detection.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match