What it does
Core capabilities at a glance
- Inference
- Openai
- Quantization
- Speech Recognition
- Speech TO Text
- Transformer
- Whisper
Deep dive
The full breakdown - performance, comparisons, and setup
faster-whisper
faster-whisper is a speech (TTS/STT) tool - Faster Whisper transcription with CTranslate2.
Overview
faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.
This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU.
GPU Benchmarks are Executed with CUDA 12.4 on a NVIDIA RTX 3070 Ti 8GB. [^1]: transformers OOM for any batch size > 1
Unlike openai-whisper, FFmpeg does not need to be installed on the system. The audio is decoded with the Python library PyAV which bundles the FFmpeg libraries in its package.
Note: The latest versions of 'ctranslate2' only support CUDA 12 and cuDNN 9. For CUDA 11 and cuDNN 8, the current workaround is downgrading to the '3.24.0' version of 'ctranslate2', for CUDA 12 and cuDNN 8, downgrade to the '4.4.0' version of 'ctranslate2', (This can be done with 'pip install --force-reinstall ctranslate2==4.4.0' or specifying the version in a 'requirements.txt').
There are multiple ways to install the NVIDIA libraries mentioned above. The recommended way is described in the official NVIDIA documentation, but we also suggest other installation methods below.
faster-whisper is open-source, written primarily in Python, with 23,464 GitHub stars under the MIT license. The latest release is v1.2.1 (2025-10-31).
Key capabilities
From the project's documentation:
- Python 3.9 or greater
- cuBLAS for CUDA 12
- cuDNN 9 for CUDA 12
- The option --model accepts a model name on the Hub or a path to a model directory.
Install
A quick way to get started (always check the official docs for the latest):
pip install nvidia-cublas-cu12 nvidia-cudnn-cu12==9.*How it fits a local-AI stack
faster-whisper runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related speech (TTS/STT) tools in the directory:
Sources
- Source code & docs: SYSTRAN/faster-whisper
Stats from GitHub, 2026-06-08.
Frequently asked
Quick answers to common questions
What is faster-whisper?
faster-whisper is a tts-stt tool for local AI workloads. Faster Whisper transcription with CTranslate2
Is faster-whisper free and open source?
Yes, faster-whisper has 23,465 GitHub stars and is licensed under MIT. You can self-host it for free on .
What hardware do I need for faster-whisper?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. faster-whisper has 23,465 GitHub stars and an active community.
Does faster-whisper support GPU acceleration?
faster-whisper's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to faster-whisper?
Popular alternatives include other tts-stt tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does faster-whisper cost?
faster-whisper is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware
Comments coming soon
Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.