IVASTbot-GPT

IVASTbot-GPT is a voice-based chatbot that uses speech-to-text (STT) and text-to-speech (TTS) technologies to interact with users. It leverages the OpenAI GPT-3.5 model for generating responses and supports Vietnamese language.

Features

• Record audio and convert it to text using the PhoWhisper model.
• Generate responses using the OpenAI GPT-3.5 model.
• Convert text responses to speech using the gTTS library.
• Supports Vietnamese language.

Installation

1. Clone the repository:

   git clone https://github.com/ngoManhDUY/IVASTbot-GPT.git
   cd IVASTbot-GPT

2. Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`

3. Install the required packages:

   pip install -r requirements.txt

Usage

1. Run the main script:

   python main.py

2. Follow the prompts to interact with the chatbot:

   • Speak your question into the microphone.
   • The chatbot will transcribe your question, generate a response, and speak the response back to you.

3. To stop the chatbot, say "Chào tạm biệt".

File Structure

• main.py: Main script for recording audio, transcribing it, generating responses, and converting responses to speech.
• chat_gpt.py: Script for interacting with the OpenAI GPT-3.5 model.
• requirements.txt: List of required Python packages.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgements

• OpenAI for the GPT-3.5 model.
• gTTS for the text-to-speech functionality.
• PhoWhisper for the speech-to-text model.
• Hugging Face Transformers for the ASR pipeline.
• Noisereduce for noise reduction.
• Librosa for additional audio processing.