The Recipe Audio Assistant is a user-friendly web application designed to guide users through the cooking process step by step. It generates natural language explanations for each step of the recipe and suggests ingredient substitutions when needed, ensuring a seamless cooking experience.
-
Step-by-step Cooking Guidance
- Provides clear instructions for each step in the recipe.
-
Ingredient Substitution Suggestions
- Offers alternative ingredients in case the required ones are unavailable.
-
Interactive User Interface
- Streamlit-based interface for ease of use and accessibility.
-
Natural Language Explanations
- Powered by GPT-2, the system generates human-like explanations for cooking steps.
- Streamlit: For building the interactive web-based UI.
- TensorFlow GPT-2: For generating instructions and explanations.
- ChromaDB: A vector database used for storing and retrieving recipe data efficiently.
- GTTS: Tool for Text to Speech conversion
-
Clone the repository:
git clone [https://github.com/yourusername/recipe-audio-assistant.git](https://github.com/S-iddharth/RecipeAudioAssistant) cd recipe-audio-assistant -
Install the required dependencies:
pip install -r requirements.txt
-
Run the application:
streamlit run app.py
-
Select a Recipe:
- Enter Recipe Name to choose from available recipes.
-
Follow Step-by-Step Instructions:
- View and interact with each step by clicking Get Recipe.
-
Request Audio:
- Click the "Speak Recipe" button to get detailed audio guidance for any step.
-
Get Substitution Suggestions:
- Enter the Ingredient Name and Use the "Get Alternatives" button for alternative ingredients.
The application can be deployed on Azure using Azure App Service. Ensure the following:
- All required dependencies are included in your environment.
- Instruction Clarity: Rate how well the steps are explained.
- Substitution Relevance: Evaluate the accuracy and relevance of ingredient alternatives.
This project is licensed under the MIT License. See the LICENSE file for details.
Contributions are welcome! Please fork the repository and submit a pull request.