Faster-Whisper

Whisper reimplementation on CTranslate2 for faster local ASR.

Install Repository Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 8 GB
Gpu: Optional · 4 GB VRAM helps
Docker: Yes
Setup: Intermediate
Deploy as: Local
Commercial use: Allowed

MIT. GPU optional; CPU is usable on short clips.

Project.

Fetched Sep 12, 2026¹

License: MIT
Stars: 25.4k¹
Forks: 2.1k¹
Open issues: 290¹
Language: Python¹
Last commit: Nov 19, 2025¹
Latest release: Jul 15, 2026
Tags: asrctranslate2transcription

About.

Faster-Whisper keeps the Whisper model family and cuts latency with CTranslate2. Common backend under transcription UIs. Still a library, not a chat product.

batched inference · VAD filter · word timestamps

Alternatives.

Nearby.

All Speech AI

WWhisperOpenAI’s speech-to-text model you can run locally.Compare
PPiperFast local neural text-to-speech that runs on CPU.Compare
Wwhisper.cppC/C++ port of Whisper for fast local transcription.Compare
WwhisperXWhisper with word-level timestamps and speaker diarization for real subtitles.Compare
Kkokoro-onnxKokoro 82M voices as ONNX — real-time TTS on CPU with zero GPU.Compare