explaingit

systran/faster-whisper

Analysis updated 2026-06-21

★ 22,671PythonAudience · developerComplexity · 3/5Setup · moderate

TLDR

A Python library that converts spoken audio to text up to four times faster than OpenAI's original Whisper model, using less memory, with support for GPU acceleration and batch processing of multiple files.

Mindmap

mindmap
  root((repo))
    What it does
      Audio to text transcription
      4x faster than original Whisper
      Less memory usage
    How it works
      CTranslate2 inference engine
      Timed text segments output
      int8 compression mode
    Acceleration options
      GPU via CUDA
      CPU fallback
      Batch processing
    Use cases
      Podcast transcription
      Subtitle generation
      Meeting notes
      Voice assistants
    Tech stack
      Python
      CTranslate2
      CUDA
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Transcribe podcast episodes or interview recordings into time-stamped text files automatically.

USE CASE 2

Generate subtitle files for video content by extracting spoken words with timestamps from audio tracks.

USE CASE 3

Build a meeting notes tool that converts recorded calls into searchable text transcripts.

USE CASE 4

Process a large batch of audio files quickly using GPU acceleration to get transcripts at scale.

What is it built with?

PythonCTranslate2CUDA

How does it compare?

systran/faster-whisperserengil/deepfacesuperclaude-org/superclaude_framework
Stars22,67122,67722,610
LanguagePythonPythonPython
Setup difficultymoderatemoderatemoderate
Complexity3/52/52/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

GPU acceleration requires an NVIDIA GPU with CUDA, CPU mode works without a GPU but is slower.

In plain English

Faster Whisper is a Python library that converts spoken audio into written text, using a rebuilt version of OpenAI's Whisper speech-recognition model. The key idea is speed: by rebuilding Whisper on top of a faster inference engine called CTranslate2, it can transcribe audio up to four times faster than the original while using less memory. The library works by loading a speech model, pointing it at an audio file, and getting back a stream of timed text segments, essentially time-stamped transcripts. It supports running on a GPU for top speed or on a regular CPU, and it can use a compressed "int8" mode to further cut down memory usage without much accuracy loss. You can also process multiple audio clips at once in a batched mode for even faster throughput. Someone would use this when they need to convert large amounts of audio or video to text quickly, think podcast transcription, meeting notes, subtitle generation, or building a voice assistant. It is also a good fit for anyone who found the original Whisper too slow and wants a drop-in replacement that needs less computing power. The stack is Python, with the CTranslate2 engine under the hood and NVIDIA CUDA for GPU acceleration. Audio decoding is handled internally without needing to install separate tools.

Copy-paste prompts

Prompt 1
Using faster-whisper in Python, write a script that transcribes an MP3 file and saves the output as a plain-text file with a timestamp and text for each spoken segment.
Prompt 2
Show me how to run faster-whisper in int8 mode on a CPU so I can transcribe audio on a machine with no GPU.
Prompt 3
Help me write a Python script that uses faster-whisper to generate an SRT subtitle file from a video's audio track.
Prompt 4
How do I use faster-whisper's batched transcription mode to process a folder of 50 audio files as quickly as possible?
Prompt 5
Write a Python function that uses faster-whisper to automatically detect the language of an audio clip and then transcribe it in that language.

Frequently asked questions

What is faster-whisper?

A Python library that converts spoken audio to text up to four times faster than OpenAI's original Whisper model, using less memory, with support for GPU acceleration and batch processing of multiple files.

What language is faster-whisper written in?

Mainly Python. The stack also includes Python, CTranslate2, CUDA.

How hard is faster-whisper to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is faster-whisper for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub systran on gitmyhub

Verify against the repo before relying on details.

Alternatives & similar repos