faster-whisper

by SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

TL;DR

4× faster than reference Whisper using CTranslate2 — production sweet spot.

Best for production batch transcription on GPU, cheapest $/hour of any hosted Whisper variant. Pricing: free.

Category
Open source
License
MIT
Stars
★ 22.3k
Last push
2025-11-19
Pricing
free
Platforms
Linux, macOS, Windows, GPU

What it is

faster-whisper wraps Whisper in CTranslate2 — a tuned inference engine for transformer models. On a single consumer GPU it's ~4× faster than reference Whisper and uses ~2× less VRAM, with essentially identical accuracy. This is what most production Whisper stacks actually run, including Whipscribe. MIT-licensed and stable.

Best for: Production batch transcription on GPU, cheapest $/hour of any hosted Whisper variant.
Watch out for: No diarization (pair with pyannote or whisperX); model conversion step can trip people up the first time.

Install / use

pip install faster-whisper

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

Links

GitHub repo ↗

faster-whisper vs Whipscribe

Featurefaster-whisperWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, Windows, GPUWeb, API, MCP
Cost comparison: faster-whisper vs Whipscribe
faster-whisper at free · Whipscribe free beta · 99 languages · data checked 2026-04-24.
How Whipscribe handles your audio
Paste a URL, upload a file, or record — get a diarized transcript in under a minute.

Alternatives to faster-whisper

Frequently asked about faster-whisper

Is faster-whisper more accurate than OpenAI Whisper?

Accuracy is essentially identical — same model weights, same training. The difference is runtime speed and VRAM usage, both of which faster-whisper improves materially. Any measurable WER gap is in the noise.

How much faster is faster-whisper?

Published benchmarks show roughly 4x faster inference on a single GPU versus the reference openai-whisper package, with ~2x lower VRAM. Your mileage varies with batch size, model size, and hardware.

Does faster-whisper support diarization?

No. It handles transcription only. Combine it with pyannote for speaker labels, or use whisperX, which integrates both.

What license is faster-whisper?

MIT — permissive for commercial and non-commercial use. CTranslate2 (the underlying engine) is also MIT-licensed.

Can faster-whisper run on CPU?

Yes. Use compute_type='int8' and a smaller model (base or small) for acceptable speed. For production CPU workloads, whisper.cpp is usually faster.

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, we're one click away.

Try Whipscribe →