AntonioAEMartins/speech-to-text

A Python toolkit for automated audio transcription using OpenAI's Whisper model. It handles large audio files through intelligent compression, parallel chunk processing, and correction of technical terms. Features include audio size optimization and smart text formatting, making it ideal for transcribing meetings and technical conversations.

Language: Python - Size: 19.7 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0