Skip to main content

FADE is a project aimed at detecting fallacies in various forms of speech. Upgrading and optimizing this tool will enable the identification of unethical, manipulative, and persuasive discourse from politicians, influencers, and even our friends and families.

Project description

FADE: Empowering everyone to detect fallacies in real time with ease!

[Our Website] | [Our Research Website] | [pré-print FADE paper]

## Table of contents

Overview

FADE is a project aimed at detecting fallacies in various forms of speech. Upgrading and optimizing this tool will enable the identification of unethical, manipulative, and persuasive discourse from politicians, influencers, and even our friends and families.

Roadmap

  • Implement a video-transcription feature
  • Optimize current prompt system
  • Fine-tune a LLM to test if the results are better

Installation

We recommend setting up a virtual environment before starting to work with FADE:

  • Create a virtual environment: python -m venv .venv
  • Activate your virtual environment: .\.venv\Scripts\activate

To begin using our library, simply install it via pip: pip install fade

Setting Up FADE

Before running the bellow script create a .env file and place your API Key inside it: GROQ_API_KEY="your_api_key".

Simple detection in string

from src.fade.fallacy_detector import detect_fallacy

phrase = "I'm better than you because I'm taller than you"

print(detect_fallacy(phrase))

Simple detection in speech-to-text

For this feature you have to setup you google cloud feature first and your google-cloud-speech api.

import sys
import os

sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))

from src.fade.transcription_features.live_transcription import main as lt
from src.fade.fallacy_detector import *

text = lt()

print(detect_fallacy(text))

Contribuition

FADE is open-source and we welcome contributions. If you're looking to contribute, please:

  • Fork the repository.
  • Create a new branch for your feature.
  • Add your feature or improvement.
  • Send a pull request.

Issue Reporting

If you encounter any problems while using our library, please don't hesitate to create an issue on GitHub. When reporting issues, please provide as much detail as possible, including:

  • Steps to reproduce the issue
  • Expected behavior
  • Actual behavior
  • Any error messages or stack traces

Your feedback is valuable to us and will help improve the library for everyone. Thank you for contributing to the project!

Contact Us

If you have any questions, suggestions, or feedback regarding FADE, please feel free to reach out to us:

We are committed to improving FADE based on your input and look forward to hearing from you!

Ackonwledgments

A heartfelt thank you to all the contributors of the Fallacie score board repo. Your dedication and hard work have been instrumental in making this project possible. We deeply appreciate the entire community's support and involvement.

License

FADE is released under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

python_fade-0.0.1.tar.gz (9.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

python_fade-0.0.1-py3-none-any.whl (8.0 kB view details)

Uploaded Python 3

File details

Details for the file python_fade-0.0.1.tar.gz.

File metadata

  • Download URL: python_fade-0.0.1.tar.gz
  • Upload date:
  • Size: 9.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.2

File hashes

Hashes for python_fade-0.0.1.tar.gz
Algorithm Hash digest
SHA256 446c06edbc57ffd61983ebc0e46ea276f185250ae4839ff650db20dd0871f4d5
MD5 7c6f13dba9404544431aedcebf5b1dac
BLAKE2b-256 b2d8d5eb8480ea433e9363f430c20776d113bff62455664a4d3c82be0af65afd

See more details on using hashes here.

File details

Details for the file python_fade-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: python_fade-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 8.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.2

File hashes

Hashes for python_fade-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a06ae92c5b557ad9e949d90a41e27902dd8b2fdb1ee946febb724cdff5b8ae7e
MD5 ef88ed2a4f78220bab0c1207ee5a4c1c
BLAKE2b-256 53f58c8732cdd8179be546e35b3a3fefd08b8376bdba6c21721fc1c52aa1a7e5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page