Whisper
OpenAI’s open-source speech recognition and translation model.
- Star 数
- 110.5K
- Fork 数
- 13.4K
- 未关闭 Issue
- 171
- 最近提交
- 2026-08-31
数据来自 GitHub API · 更新于 2026-10-15
Whisper 是什么？
Whisper transcribes speech in nearly 100 languages and can translate it into English. The open-source package includes a CLI and Python API with model sizes from tiny to large, plus the faster “turbo” model.
主要功能
- Multilingual transcription and translation to English
- Model sizes from tiny to large-v3 and turbo
- SRT/VTT subtitle output
- Language detection
系统要求
- 平台
- Windows · macOS · Linux
- 显卡
- Optional; NVIDIA recommended for large models
- 显存
- ~1 GB (tiny) to ~10 GB (large)
- Python
- 3.8–3.11
- 备注
- Requires ffmpeg on PATH.
如何安装 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 ffmpeg (e.g. brew install ffmpeg, sudo apt install ffmpeg or choco install ffmpeg), then Whisper.
pip install -U openai-whisper - 2Transcribe a file.
whisper audio.mp3 --model turbo --output_format srt
优势
- Excellent accuracy across languages
- MIT license
不足
- Slow on CPU
- Can hallucinate on silence
Whisper 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| Whisper OpenAI’s open-source speech recognition and translation model. | 110.5K | MIT | ~1 GB (tiny) to ~10 GB (large) | |
| faster-whisper Whisper reimplemented on CTranslate2 — up to 4× faster with less memory. | 25.9K | MIT | — | |
| whisper.cpp Whisper in plain C/C++ — fast on CPUs, Apple Silicon and mobile. | 54.4K | MIT | — | |
| WhisperX Fast transcription with word-level timestamps and speaker diarization. | 24.6K | BSD-2-Clause | — | |
| 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
Whisper 免费吗？
是的——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。
Whisper 支持 Windows、Mac 和 Linux 吗？
Whisper 支持：Windows, macOS, Linux。
运行 Whisper 需要什么配置？
Optional; NVIDIA recommended for large models. VRAM: ~1 GB (tiny) to ~10 GB (large)
如何安装 Whisper？
1. Install ffmpeg (e.g. brew install ffmpeg, sudo apt install ffmpeg or choco install ffmpeg), then Whisper. 2. Transcribe a file.
Whisper 有哪些好的替代品？
常见替代品包括 faster-whisper, whisper.cpp, WhisperX, Coqui TTS，详见本页对比表。