Cursed-GPT

CursedGPT leverages the Hugging Face Transformers library to interact with a pre-trained GPT-2 model. It employs TensorFlow for model management and AutoTokenizer for efficient tokenization. The script enables users to input prompts interactively, generating text responses from the GPT-2 model.

GitHub: Cursed-GPT

Scripts:

• main.py The selection menu for CursedGPT
• app.py Run CursedGPT as a web-server

/scripts/

• transformer.py Run CursedGPT
• transformer_t2s.py Run CursedGPT with text-to-speech functionality
• transformer_s2t2s.py Run CursedGPT with speech-to-text-to-speech functionality
• transformer_webcam.py Run CursedGPT with webcam functionality
• install_dependencies.py Install dependencies

/scripts/system

• generate_text.py The GPT text generator
• clean_text.py Clean text from recorded voice audio
• stt.py Speech-to-text
• tts.py Text-to-speech
• capture_photo.py Capture photo with a webcam
• play_audio.py Play generated audio

How to Run:

    pip install -r requirements.txt
    python main.py
    chmod +x setup.sh
    

Requirements:

    transformers==4.37.1
    tensorflow==2.14.0
    torch==2.1.1
    torchvision==0.16.1
    torchaudio==2.1.1
    flask==3.0.0
    gtts==2.5.0
    pyaudio==0.2.14 
    pydub==0.25.1
    beautifulsoup4==4.10.0
    SpeechRecognition==3.10.1
    

Languages Used in Cursed-GPT