Siri Clone

The project involved recording 4-second monophonic audio clips in wav format, containing questions. These audio clips were then transcribed into text using AssemblyAI's API. The next step was to utilize OpenAI's API, which had a GPT-3 backend (Davinci variant), to generate answers. The length of the answers was capped at 100 tokens to ensure conciseness and clarity. The objective was to utilize cutting-edge technology to efficiently transcribe audio into text and generate concise answers to questions.

Project Organization

├── LICENSE
├── Makefile                  <- Makefile with commands like `make environment` or `make requirements`
├── README.md                 <- The top-level README for developers using this project
├── test_environment.py       <- Script to test virtual environment
├── readme-assets             <- Contains images to be used in README.md
├── data
│   └── audio-recording       <- Contains audio recordings of user's questions
│
├── reports                   <- Generated analysis as HTML, PDF, LaTeX, etc.
│   └── figures               <- Generated graphics and figures to be used in reporting
│
├── requirements.txt          <- The requirements file for reproducing the analysis environment
│
└── src                       <- Source code for use in this project
    ├── __init__.py           <- Makes src a Python module
    │
    ├── audio-processing      <- Scripts to get basic audio data and visualizations
    │   ├── audio_processing_basics.py
    │   └── plot_audio.py
    │
    ├── record_mic.py         <- Script to record 4-second audio clips (containing questions)
    ├── speech_to_text.py     <- Script to convert speech to text with AssemblyAI API
    ├── openai_response.py    <- Script to feed transcribed question to OpenAI API to get response                    
    ├── main.py               <- Driver program
    └── api_secrets.py        <- Used to store API keys for OpenAI and AssemblyAI

Prerequisites

Before you begin, ensure you have met the following requirements:

You have a Linux/Mac/Windows machine.
You have installed a python distribution. conda is preferred.
You have installed pip.
You have installed make.

Setup

Clone the repo

git clone https://github.com/himalayasharma/siri-clone.git

Traverse into project directory.
Create virtual environment.
```
make create_environment
```
Activate virtual environment.
Download and install all required packages.
```
make requirements
```
Start application.
```
make app
```

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated. If you have a suggestion that would make this better, please fork the repo and create a pull request. Don't forget to give the project a star! Thanks again!

Fork this repository.
Create a branch: git checkout -b <branch_name>.
Make your changes and commit them: git commit -m '<commit_message>'
Push to the original branch: git push origin <project_name>/<location>
Create the pull request.

Alternatively see the GitHub documentation on creating a pull request.

License

Distributed under the MIT License. See LICENSE.txt for more information.

himalayasharma/siri-clone