Audio to Text Converter
This desktop application transcribes live or recorded audio converting spoken words into written text with high accuracy and in real time.
How it works
It is designed to handle lectures and other educational content so that students can focus on the material without worrying about missing crucial points. To handle the audio data, process it, and convert it into text form I used PyAudio, torch, and Whisper. PyAudio opens an audio stream that captures live audio data handled in a separate thread to keep the GUI responsive. Whisper library converts the audio stream into text. This text transcription happens in real time with frequent updates.