|
--- |
|
title: Abuse HateSpe Profanity Detector App |
|
emoji: 🚀 |
|
colorFrom: purple |
|
colorTo: blue |
|
sdk: gradio |
|
sdk_version: 4.44.0 |
|
app_file: app.py |
|
pinned: false |
|
license: apache-2.0 |
|
--- |
|
|
|
### Abusive Langauge, Hate Speech and Profanity Detection System using Pre-trained BERT models |
|
|
|
This is an application for detecting abusive language, hate speech and profanity in a text speech using pre-trained Bert Transfomer-based models found at [Hugging Facing Hub](https://huggingface.co). The models used are as follow: |
|
- Abusive Language: **[Hate-speech-CNERG/english-abusive-MuRIL](https://huggingface.co/Hate-speech-CNERG/english-abusive-MuRIL)** a model trained for detecting abusive speech in English. It is finetuned on MuRIL model using English abusive speech dataset |
|
- Hate Speech: **[cardiffnlp/twitter-roberta-base-hate-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-hate-latest)** this model is a fine-tuned version of cardiffnlp/twitter-roberta-base-2022-154m for binary hate-speech classification. A combination of 13 different hate-speech datasets in the English language were used to fine-tune the model. |
|
- Profanity: **[tarekziade/pardonmyai](https://huggingface.co/tarekziade/pardonmyai)** a fine-tuned model that detects profanity in text. |
|
|
