Whisper Voice Transcription - Demo | OpenAI | Python | Gradio
Автор: arifulislamat
Загружено: 2025-09-25
Просмотров: 88
A Python-based audio transcription tool (STT) using OpenAI's Whisper model with configurable output formats and automated file organization.
✨ Features
🌐 Web Interface: User-friendly Gradio web UI for easy drag-and-drop transcription
💻 Command Line Interface: Full CLI support for automation and scripting
Multiple Output Formats: SRT, TXT, JSON, VTT, TSV
CUDA GPU Acceleration: Automatic NVIDIA GPU detection for faster transcription
Automatic File Organization: Timestamped output folders
Environment Configuration: .env file support for default settings
Input/Output Folder Structure: Organized file management
Language Detection: Auto-detect or specify language
Model Selection: Choose from different Whisper model sizes
Task Types: Transcription or translation
📂 GitHub Repository:
Access the source code and detailed instructions here: https://github.com/arifulislamat/whis...
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
![ChatGPT и Gemini устарели. Вот реально рабочий инструмент [Opal]](https://image.4k-video.ru/id-video/0RvCVXVMftE)
