Verified project record

SYSTRAN/faster-whisper

Faster Whisper re-implements OpenAI Whisper inference on CTranslate2 to deliver up to 4x faster transcription with lower memory usage on CPU and CUDA GPUs. It supports 8-bit quantization, batched inference, voice activity detection, and word-level timestamps without requiring a system-wide FFmpeg installation.

Project overview

Project type: Model Runtime · Audio & Speech
Use cases: Meeting Notes · Translation & Subtitles · Audio & Speech
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers needing to run Whisper transcription locally on CPU or CUDA GPUs with reduced memory usage.
Workloads requiring batched transcription, VAD filtering, or Distil-Whisper support.

Key capabilities

Supports running transcription on both CPU and CUDA GPUs with various compute types including float16 and int8.
Provides a BatchedInferencePipeline drop-in replacement for significantly faster batched transcription.
Integrates Silero VAD to filter out parts of audio without speech.
Includes a script to convert Transformers-compatible Whisper models to CTranslate2 format.
Generates precise start and end timestamps for individual words during transcription.
Natively supports running Distil-Whisper checkpoints like distil-large-v3.

Limitations and risks

The latest CTranslate2 version only supports CUDA 12 and cuDNN 9.

Getting started

Install the library easily via a standard pip command without compiling dependencies locally.

Evidence and sources

Release: faster-whisper 1.2.1
README: **faster-whisper** is a reimplementation of OpenAI's Whisper model using [CTranslate2](https://github.com/OpenNMT/CTranslate2/), which is a fast inference engine for Transformer m…
README: | faster-whisper | fp16 | 5 | 1m03s | 4525MB | | faster-whisper (`batch_size=8`) | fp16 | 5 | 17s | 6090MB |
README: Unlike openai-whisper, FFmpeg does **not** need to be installed on the system. The audio is decoded with the Python library [PyAV](https://github.com/PyAV-Org/PyAV) which bundles…
README: **Note**: The latest versions of `ctranslate2` only support CUDA 12 and cuDNN 9.

Reviewed at: 2026-07-17T11:04:26Z