This Python tool allows you to transcribe audio and video files into text using OpenAI's Whisper model. It provides the option to either scan a directory for files or manually select a file for transcription. You can also choose to run the transcription on either a CPU or GPU.
- Python 3.8 or higher
- Virtual Environment (recommended)
whisperlibrarytorchlibraryffmpeg(for video/audio processing)
-
Clone this repository:
git clone https://github.com/yourusername/Transcript-Creator.git
-
cd Transcript-Creator
-
python -m venv .venv recommended
-
Activate The Virtual Enviroment Windows: .venv\Scripts\activate MacOS/Linux: source .venv/bin/activate
-
pip install -r requirements.txt
-
You will need to install ffmpeg. Would recommend searching up a Youtube video on how to install https://ffmpeg.org/download.html
-
The program will prompt with overriding a prior transcript that's already been created say "yes" if you want to override it, or if it was never made
-
You can specify a directory or just say local and search the given folder