https://github.com/Purfview/whisper-standalone-win/discussions/29 从134.5 版本开始,Whisper-Faster 支持按目录、文件列表或通配符进行批处理。 并且有新的 --batch_recursive 参数。 几个使用示例: whisper-faster.exe "D:\Clips\*.mkv" --check_files --language=en --model=medium -o=source whisper-fa...
以及详细过程 | faster-whisper和openai-whisper对比更多内容欢迎关注up 开源faster whisper地址:https://github.com/SYSTRAN/faster-whisper cuBLAS and cuDNN下载地址:https://github.com/Purfview/whisper-standalone-win/releases/tag/libs 文章参考地址:https://blog.lukeewin.top/archives/faster-whisper-webui ...
http://github.com/Purfview/whisper-standalone-win/releases/tag/libs 下载解压,根据提示放入相应位置。 安装依赖库: pip install nvidia-cublas-cu11 nvidia-cudnn-cu11 然后就可以使用 GPU 运行了。 Python 代码: from faster_whisper import WhisperModel model_size = "large-v3" # 使用 GPU 运行,指定精...
在相同精度的情况下,faster-whisper 的速度比 OpenAI whisper 快 4 倍,并且使用更少的内存。 这是faster-whisper 与 OpenAI whisper 的测试对比结果,使用了一个13分钟的音频做的测试。 OpenAI whisper 用了4分30秒,faster-whisper 只用了54秒。 并且,faster-whisper 使用的 CPU 和 GPU 都只有 OpenAI whisper 的...
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python. subtitlesspeech-recognitionopenaispeech-to-textwhisperasrspeaker-diarizationuvrtranscriberdiarizationfaster-whisperctranslate2whisperxwhisper-fastervocal-extractor ...
pip install faster-whisper # 更新 pip install -U faster-whisper 1. 2. 3. 4. CUDA 的安装 我试过直接下载https://developer.nvidia.com/cuda-downloads 或者 https:///Purfview/whisper-standalone-win/releases/tag/libs解压存档并将对应库放在 PATH 目录中。
github.com/Purfview/whisper-standalone-win/releases/tag/libs 下载解压,根据提示放入相应位置。 安装依赖库: pip install nvidia-cublas-cu11 nvidia-cudnn-cu11 然后就可以使用 GPU 运行了。 Python 代码: from faster_whisper import WhisperModel
* [whisper-diarize](https://github.com/MahmoudAshraf97/whisper-diarization) is a speaker diarization tool that is based on `faster-whisper` and nvidia nemo. * [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) contains the portable ready to run binaries of `faster...
Faster-Whisper executables are x86-64 compatible with Windows 7, Linux v5.4, macOS v10.15 and above. Meant to be used in command-line interface or in programs like Subtitle Edit, Tero Subtitler, FFAStrans. Faster-Whisper is much faster & better than OpenAI's Whisper, and it requires less ...