Skip to content
  1. Home
  2. AI tools
  3. faster-whisper

faster-whisper

Whisper transcription reimplemented on CTranslate2 for speed

What it is

A Python reimplementation of Whisper on the CTranslate2 inference engine. Its README reports up to four times the speed of the reference implementation at the same accuracy with lower memory use, and supports 8-bit quantisation on CPU and GPU. For developers adding transcription to Python pipelines.

Good for

  • Transcribe long recordings in Python
  • Cut GPU memory use for Whisper models
  • Run quantised speech recognition on CPU

Install or run

pip install faster-whisper

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Python; NVIDIA cuBLAS and cuDNN libraries for GPU use

Worth knowingA library, not an app: no UI, and speaker diarisation needs separate tooling.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for design & media

See the topic →
  • ComfyUI

    Comfy-Org/ComfyUI

    Node-graph interface for image, video, audio and 3D generation

    ToolGitHub stars: 147k
  • OpenDesign

    nexu-io/open-design

    Local-first design workspace that coding agents drive via skills and MCP

    ToolGitHub stars: 107k
  • HyperFrames

    heygen-com/hyperframes

    Framework that renders HTML, CSS and animations to MP4 video

    ToolGitHub stars: 84k
  • OpenMontage

    OpenMontageInc/OpenMontage

    Agent-run video production pipelines from research to final render

    ToolGitHub stars: 80k