CheshireCC/faster-whisper-GUI

faster_whisper GUI with PySide6

What it solves

It provides a graphical user interface (GUI) for users who want to transcribe audio and video files without needing to use a command-line interface. It simplifies the process of converting speech to text and managing the resulting subtitles or transcripts.

How it works

The software acts as a visual wrapper for several high-performance speech-to-text engines, including faster-whisper and whisperX. It allows users to load, download, and convert models directly within the application. It also integrates Demucs for audio source separation (AVE) to improve transcription quality.

Who it’s for

People who need to generate subtitles or transcripts from media files and prefer a visual interface for adjusting model parameters, managing batch processes, and editing timestamps.

Highlights

  • Multi-format export: Supports exporting transcriptions to srt, txt, smi, vtt, and lrc formats.
  • Engine support: Compatible with faster-whisper, whisperX, and the large-v3 model.
  • Advanced audio processing: Includes Demucs support for audio separation.
  • Detailed control: Provides full access to VAD-model and whisper-model parameters.
  • Editing tools: Features a built-in result viewer to edit timestamps.

Related

  • Project
  • Project
  • Project
  • Project