This project is a Python-based GUI application that uses OpenAI's Whisper model for audio transcription and Google Translate for text translation. It supports multiple languages, GPU acceleration, and allows users to save transcriptions and translations as text files.
.mp3
, .mp4
, .wav
) into text using the Whisper model.To run this project locally, make sure you have the following installed:
pip
package managerGUI SPOILER
The application depends on the following Python libraries:
openai-whisper
: For audio transcriptiontorch
: PyTorch for GPU accelerationpsutil
: For system resource monitoring (CPU, RAM)googletrans==4.0.0-rc1
: For text translation via Google TranslateGPUtil
: For GPU monitoring (optional)if not work follow this page https://github.com/openai/whisper