# faster-whisper

> faster-whisper runs Whisper models through the CTranslate2 engine; the README claims up to 4x the speed of openai/whisper at the same accuracy. Benchmarks show large-v2 int8 on GPU at ~2.9 GB VRAM and small int8 on CPU at ~1.5 GB RAM. Code is MIT and the converted Systran models on Hugging Face are tagged MIT. pip install; no system ffmpeg needed. Speech recognition only.

- Repository: https://github.com/SYSTRAN/faster-whisper
- Official docs: https://github.com/SYSTRAN/faster-whisper#readme
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech recognition (full). Local transcription with word timestamps and VAD filter; the README does not mention speaker diarization.
- Otter.ai: Meeting transcription (partial). Transcribes recordings locally; no live meeting capture, speaker labels or summaries.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, Python library runs on CPU or NVIDIA GPU | https://github.com/SYSTRAN/faster-whisper#faster-whisper | 2026-10-15 |
| Code licence | Confirmed | MIT | https://github.com/SYSTRAN/faster-whisper/blob/master/LICENSE | 2026-10-15 |
| Model weights licence | Confirmed | MIT (Systran CTranslate2 conversions of Whisper on Hugging Face, e.g. Systran/faster-whisper-large-v3, ungated) | https://huggingface.co/Systran/faster-whisper-large-v3 | 2026-10-15 |
| Commercial use | Confirmed | Yes, MIT code and MIT-tagged default model weights | https://huggingface.co/Systran/faster-whisper-large-v3 | 2026-10-15 |
| Paid services needed? | Confirmed | None required | https://github.com/SYSTRAN/faster-whisper#installation | 2026-10-15 |
| Hardware | Confirmed | CPU works (small model int8: ~1.5 GB RAM in README benchmark); GPU needs cuBLAS and cuDNN 9 for CUDA 12 (large-v2 int8: ~2.9 GB VRAM on an RTX 3070 Ti 8GB). These are benchmark figures, not stated minimums | https://github.com/SYSTRAN/faster-whisper#benchmark | 2026-10-15 |
| Operating systems | Partial | Windows and Linux GPU library install paths documented; macOS not stated for this project | https://github.com/SYSTRAN/faster-whisper#gpu | 2026-10-15 |
| Setup effort | Confirmed | Easy; pip install faster-whisper, Python 3.9+. GPU use additionally needs NVIDIA cuBLAS/cuDNN | https://github.com/SYSTRAN/faster-whisper#requirements | 2026-10-15 |

GitHub: 25887 stars, 2141 forks, last push 2026-10-15, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/faster-whisper). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.