Insanely Fast Whisper GPU-Accelerated Speech Transcription CLI

Insanely Fast Whisper is a CLI tool that transcribes audio at extreme speeds using OpenAI Whisper models with Hugging Face Transformers, Flash Attention 2, and batched inference. It can transcribe 150 minutes of audio in under 98 seconds on a GPU.

Insanely Fast Whisper GPU-Accelerated Speech Transcription CLI

Insanely Fast Whisper is a CLI tool that transcribes audio at extreme speeds using OpenAI Whisper models with Hugging Face Transformers, Flash Attention 2, and batched inference. It can transcribe 150 minutes of audio in under 98 seconds on a GPU.

Installation

Method 1, Agent Skill Exchange

Method 2, Git clone

git clone https://github.com/agentskillexchange/skills.git && cd skills/skills/insanely-fast-whisper-gpu-transcription

Method 3, Download ZIP

  • Download the repository ZIP and extract skills/insanely-fast-whisper-gpu-transcription.

Method 4, Manual copy

  • Copy this skill folder into your local skills directory, then reload your agent tooling.

Method 5, Fork and sync

  • Fork the repository if you want to maintain local edits while syncing upstream changes.

Source