"you suck, but you're not going to do anything about it."Overview
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. To improve the user experience, unnecessary warning messages related to the transformers library are effectively suppressed.
Scripts
- main.py: The selection menu for CursedGPT
- app.py: Run CursedGPT as a web-server
- 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
- 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
Environment Setup
python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txtpip install torch torchvision torchaudiopython main.pypython app.py