Note: For all these methods below, keep in mind the above note regarding CUDA versions.

Use Docker

cuBLAS is included in the official NVIDIA CUDA runtime Docker images, such as nvidia/cuda:12.8.1-runtime-ubuntu22.04.

Install with pip (Linux only)

On Linux cuBLAS can be installed with pip. Note that LD_LIBRARY_PATH must be set before launching Python.

pip install nvidia-cublas-cu12

export LD_LIBRARY_PATH=$(python3 -c 'import os, nvidia.cublas; print(os.path.dirname(nvidia.cublas.__path__[0]) + "/cublas/lib")')

Install the master branch

pip install --force-reinstall "faster-whisper2 @ https://github.com/BBC-Esq/faster-whisper2/archive/refs/heads/master.tar.gz"

Install a specific commit

pip install --force-reinstall "faster-whisper2 @ https://github.com/BBC-Esq/faster-whisper2/archive/a4f1cc8f11433e454c3934442b5e1a4ed5e865c3.tar.gz"

Here is a non exhaustive list of open-source projects using faster-whisper. Feel free to add your project to the list!

• speaches is an OpenAI compatible server using faster-whisper. It's easily deployable with Docker, works with OpenAI SDKs/CLI, supports streaming, and live transcription.
• WhisperX is an award-winning Python library that offers speaker diarization and accurate word-level timestamps using wav2vec2 alignment
• whisper-ctranslate2 is a command line client based on faster-whisper and compatible with the original client from openai/whisper.
• whisper-diarize is a speaker diarization tool that is based on faster-whisper and NVIDIA NeMo.
• whisper-standalone-win Standalone CLI executables of faster-whisper for Windows, Linux & macOS.
• asr-sd-pipeline provides a scalable, modular, end to end multi-speaker speech to text solution implemented using AzureML pipelines.
• Open-Lyrics is a Python library that transcribes voice files using faster-whisper, and translates/polishes the resulting text into .lrc files in the desired language using OpenAI-GPT.
• wscribe is a flexible transcript generation tool supporting faster-whisper, it can export word level transcript and the exported transcript then can be edited with wscribe-editor
• aTrain is a graphical user interface implementation of faster-whisper developed at the BANDAS-Center at the University of Graz for transcription and diarization in Windows (Windows Store App) and Linux.
• Whisper-Streaming implements real-time mode for offline Whisper-like speech-to-text models with faster-whisper as the most recommended back-end. It implements a streaming policy with self-adaptive latency based on the actual source complexity, and demonstrates the state of the art.
• WhisperLive is a nearly-live implementation of OpenAI's Whisper which uses faster-whisper as the backend to transcribe audio in real-time.
• Faster-Whisper-Transcriber is a simple but reliable voice transcriber that provides a user-friendly interface.
• Open-dubbing is open dubbing is an AI dubbing system which uses machine learning models to automatically translate and synchronize audio dialogue into different languages.
• Whisper-FastAPI whisper-fastapi is a very simple script that provides an API backend compatible with OpenAI, HomeAssistant, and Konele (Android voice typing) formats.

When you specify a compute_type, faster-whisper2 validates that it is compatible with your device before downloading anything. If an incompatible combination is detected, a clear error is raised. For quantized types (e.g. int8), the library automatically downloads the best source precision for your hardware and CTranslate2 handles the runtime conversion.

Supported compute types by device

Which model precision is downloaded

CUDA compute capability by GPU generation