faster-whisper
Whisper reimplemented on CTranslate2 — up to 4× faster with less memory.
- Star 数
- 25.9K
- Fork 数
- 2.1K
- 未关闭 Issue
- 24
- 最近提交
- 2026-10-13
数据来自 GitHub API · 更新于 2026-10-15
faster-whisper 是什么？
faster-whisper runs Whisper models through the CTranslate2 inference engine, cutting time and memory use with the same accuracy. It supports 8-bit quantization on CPU and GPU and built-in voice activity detection.
主要功能
- Up to 4× faster than openai/whisper
- INT8 quantization on CPU and GPU
- Silero VAD filtering
- Word-level timestamps
系统要求
- 平台
- Windows · macOS · Linux
- 显卡
- Optional; NVIDIA with cuBLAS and cuDNN for GPU
- Python
- 3.9+
如何安装 faster-whisper
根据项目 README 整理。开源项目更新很快，请以 GitHub 页面上的最新说明为准。
pip
- 1Install.
pip install faster-whisper - 2Transcribe in Python.
from faster_whisper import WhisperModel model = WhisperModel("large-v3", device="cuda", compute_type="float16") segments, info = model.transcribe("audio.mp3", beam_size=5) for s in segments: print(f"[{s.start:.2f}s -> {s.end:.2f}s] {s.text}")
优势
- Much faster than the original
- No ffmpeg dependency
不足
- Library only — no UI
faster-whisper 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| faster-whisper Whisper reimplemented on CTranslate2 — up to 4× faster with less memory. | 25.9K | MIT | — | |
| Whisper OpenAI’s open-source speech recognition and translation model. | 110.5K | MIT | ~1 GB (tiny) to ~10 GB (large) | |
| WhisperX Fast transcription with word-level timestamps and speaker diarization. | 24.6K | BSD-2-Clause | — | |
| whisper.cpp Whisper in plain C/C++ — fast on CPUs, Apple Silicon and mobile. | 54.4K | MIT | — | |
| Coqui TTS Deep-learning text-to-speech toolkit, including the XTTS voice cloning model. | 46.1K | MPL-2.0 | — | |
| GPT-SoVITS Few-shot voice cloning and TTS with a full training WebUI. | 62.8K | MIT | 6 GB+ |
常见问题
faster-whisper 免费吗？
是的——faster-whisper 是开源软件，采用 MIT 许可证。商用前请确认软件及模型权重的许可条款。
faster-whisper 支持 Windows、Mac 和 Linux 吗？
faster-whisper 支持：Windows, macOS, Linux。
运行 faster-whisper 需要什么配置？
Optional; NVIDIA with cuBLAS and cuDNN for GPU
如何安装 faster-whisper？
1. Install. 2. Transcribe in Python.
faster-whisper 有哪些好的替代品？
常见替代品包括 Whisper, WhisperX, whisper.cpp, Coqui TTS，详见本页对比表。