This is a transcription application that listens to audio input from the microphone using OpenAI's Whisper, transcribes it into text, and simulates typing the transcription in real-time wherever your cursor is on the screen.
-
Install Miniconda or Anaconda if you haven't already. You can download Miniconda from here.
-
Clone this repository to your local machine:
git clone https://github.com/badgids/transcription-app.git
-
Navigate to the project directory:
cd transcription-app -
Create a conda environment and install the required packages:
conda create -n transcribe python=3.10
-
Activate the conda environment:
conda activate transcribe
-
Install additional requirements:
pip install -r requirements.txt
-
Run the program:
python transcribe.py
-
If you don't have Miniconda or Anaconda installed, download and run the
install.batfile from the project's root directory. Follow the on-screen instructions to install Miniconda and set up the environment. -
Once Miniconda is installed, double-click the
start.batfile to activate the environment and run the program.
-
Follow steps 2-5 above for Windows.
-
Install additional requirements:
pip install -r requirements.txt
-
Run the program:
python transcribe.py
- Upon running the program, a GUI window will appear.
- Select your microphone from the dropdown menu.
- Choose the model size (tiny, base, small, medium, large) for transcription.
- Click the "Start Transcription" button to begin transcription.
- The program will transcribe the audio input from the microphone in real-time and simulate typing the transcription wherever your cursor is on the screen.
- If you encounter any issues with the installation or running the program, please open an issue on GitHub.
Contributions are welcome! If you find any bugs or have suggestions for improvement, please open a pull request or create an issue on GitHub.
This project is licensed under the MIT License.