Sign in Submit site

Faster Whisper

github.com/guillaumekln/faster-whisper AI Speech Transcription Open-source projectOpen source

Faster Whisper runs Whisper transcription through the CTranslate2 inference engine.

Visit Faster Whisper 12 alternatives
github.com/guillaumekln/faster-whisper
Faster Whisper homepage screenshot

About Faster Whisper

Faster Whisper is an open-source Python library that runs OpenAI's Whisper speech recognition model for audio transcription. It is a reimplementation built on the CTranslate2 inference engine. The project states that it is up to 4 times faster than openai/whisper at the same accuracy, while using less memory. It also says that 8-bit quantization can improve efficiency on both CPU and GPU. The published benchmarks compare time and memory for transcribing 13 minutes of audio on specific hardware, including an NVIDIA RTX 3070 Ti GPU and an Intel Core i7-12700K CPU, so results on other systems may differ.

GPU use requires NVIDIA cuBLAS and cuDNN libraries. The latest CTranslate2 versions support only CUDA 12 and cuDNN 9, and the README describes version downgrades for older setups. The library requires Python 3.9 or later. Unlike openai-whisper, it does not need FFmpeg installed separately, because audio is decoded with PyAV, which bundles FFmpeg libraries.

Key features

  • Reimplements OpenAI's Whisper speech recognition model using the CTranslate2 inference engine
  • Optional 8-bit quantization on both CPU and GPU
  • Batched transcription through a batch_size setting, shown in the benchmarks
  • Installable from PyPI with pip install faster-whisper
  • Decodes audio without a separate FFmpeg installation, using bundled PyAV libraries
  • Docker-based setup documented for NVIDIA CUDA library dependencies
Best for: Developers and technical users who want to run Whisper transcription from Python on NVIDIA GPU or CPU hardware and value speed and lower memory use.
Good for
  • The project reports up to 4 times the speed of openai/whisper at the same accuracy, with less memory use.
  • 8-bit quantization is described as a way to improve efficiency on CPU and GPU.
  • FFmpeg does not need to be installed separately because PyAV bundles the libraries.
Watch out for
  • GPU execution requires NVIDIA cuBLAS and cuDNN libraries to be installed.
  • The latest CTranslate2 versions support only CUDA 12 and cuDNN 9, and older setups require downgrading CTranslate2.
  • Benchmark figures apply to the specific hardware and settings listed in the README.

Faster Whisper at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026
open sourcepythondockerspeech recognition

Faster Whisper alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 12 alternatives

Popular in AI Speech Transcription

Well-known listings from the same topic.

All 43
Transgatetransgate.aiWavewave.coRev.airev.aiGood Tapegoodtape.ioTalkNotestalknotes.ioSpeech to Notespeechtonote.com
Related topicsAI Business ToolsAI Image GeneratorsAI Infrastructure & MLOpsAI Agents & AutomationAI Data & AnalyticsAI Chatbots & AssistantsAI Voice & AudioAI Writing Tools

Faster Whisper FAQ

Does Faster Whisper require FFmpeg to be installed?
No. Audio is decoded with the Python library PyAV, which bundles the FFmpeg libraries in its package.
What is needed to run Faster Whisper on an NVIDIA GPU?
GPU execution requires cuBLAS for CUDA 12 and cuDNN 9. The README lists several installation methods, including an official NVIDIA CUDA Docker image and pip packages on Linux.
How is Faster Whisper installed?
The module can be installed from PyPI with pip install faster-whisper.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing

Listing maintained by Chris McClure and the WebIndexly editors · Updated Oct 12, 2026 · How we rank