OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Security & Safety

Hatesonar

HateSonar is an open-source Python library for classifying text as hate speech, offensive language or neither. It returns a top class and confidence scores for the available classes, and its README says classification does not require users to train a model.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hatesonar — OpenViST project profile in AI Security & Safety.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use HateSonar when a Python application needs a documented three-class text classification result and confidence scores as one input to moderation or analysis.

Who it is for

  • Python developers building text moderation or analysis workflows.
  • Teams that want to flag potentially hateful or offensive user-generated text for human review.
  • Developers creating interfaces that display text-classification labels and confidence scores.

Documented uses

  • Classify a text string into hate speech, offensive language or neither.
  • Retrieve confidence scores alongside the predicted class.
  • Add a text-screening step to a moderation pipeline without training a model.
Before you choose

Requirements & limits

The public repository specifies an MIT license. The README lists Python 3.10 or later and installation with pip.

  • The documented output distinguishes hate speech, offensive language and neither, with a confidence value for each class.
  • The README says model training is not required for use.
  • Python 3.10 or later is the stated supported version.
  • The repository specifies the MIT license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Classify a text string in Python

Pass text to HateSonar and read its predicted class labels and confidence scores.

Before you start

  • HateSonar installed in a Python 3.10-or-later environment

Steps

  1. Import Sonar from hatesonar.

  2. Create a Sonar instance.

  3. Call ping with a text string.

  4. Read top_class and the classes entries, including their confidence values.

Expected outcome

The documented example returns a top class and confidence scores for hate speech, offensive language and neither.

Guide limitations

  • The README provides an example but does not document thresholds for decisions or a human-review policy.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Hironsan/HateSonar · Official homepage title · retained in its source language
How we review sourcesSuggest a correction