Directory › Audio & voice › faster-whisper
> GEM AUDIO & VOICE · DEVELOPMENT · LOCAL AI
faster-whisper
by SYSTRAN
Whisper reimplemented with CTranslate2: same accuracy, up to 4x faster and lighter.
View on GitHub →What it does
- 8-bit quantization to run on CPU or small GPUs
- Simple Python library to drop into your scripts and apps
- Engine behind many tools, including WhisperX
Install it
Requirements: Python 3.9+; for GPU, CUDA 12 and cuDNN 9 libraries.
Install with pip
pip install faster-whisper
The prompt for your agent
Paste it into your coding agent: it checks the requirements and installs it for you.
Claude CodeCodexCursorGemini CLIopencode
Prompt
Install faster-whisper (https://github.com/SYSTRAN/faster-whisper) on my machine.
1. Check the requirements: Python 3.9+; for GPU, CUDA 12 and cuDNN 9 libraries. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install with pip: pip install faster-whisper
3. Check that it works, then explain how to launch it and where to start.
Always review what your agent is about to run, especially install commands.