whisper.cpp icon
whisper.cpp icon

whisper.cpp

This program aims to facilitate running automatic speech recognition (ASR) locally both on CPU with near real-time speed and on many consumer GPU/Accelerator backends including CUDA, Apple's ANE and Vulkan Compute depending on compile-time flags.

60 seconds of the English language LibriVox Universal Declaration of Human Rights read by Kara Shallenberg.

Cost / License

  • Free
  • Open Source (MIT)

Platforms

  • Mac
  • Windows  MSVC and MinGW
  • Linux
  • Android
  • iPhone
  • WebAssembly
  • FreeBSD
  • Raspberry Pi
  • Docker
  • Java
60 seconds of the Chinese and English language LibriVox Universal Declaration of Human Rights read by Zhu Hong. Language set as Chinese.
60 seconds of the Chinese and English language LibriVox Universal Declaration of Human Rights read by Zhu Hong. Language set as Chinese, translation requested. Translation requires using a non-Turbo model.
whisper.cpp alternatives  
1like
8alternatives
0articles

Features

  1.  Command line interface
  2.  Speech to text
  3.  Support for NVIDIA CUDA acceleration
  4.  Speech Recognition
  5.  Local AI

 Tags

whisper.cpp News & Activities

Highlights All activities

Recent activities

whisper.cpp information

AlternativeTo Categories

AI Tools & Services, OS & Utilities

GitHub repository

  •  53,714 Stars
  •  6,164 Forks
  •  350 Open Issues
  •   Updated  
View on GitHub

Popular alternatives

View all
whisper.cpp was added to AlternativeTo by Samenaga on and this page was last updated .
No comments or reviews, maybe you want to be first?

Official Links

AppStores & Other Links

What is whisper.cpp?

This program aims to facilitate running automatic speech recognition (ASR) locally both on CPU with near real-time speed and on many consumer GPU/Accelerator backends including CUDA, Apple's ANE and Vulkan Compute depending on compile-time flags.

It can open flac, mp3, ogg and wav files by default, and many more if compiled with FFMPEG support. It can format its output as srt (default), vtt, plain text, json and more; either in their original languages or translated to English.

The backing project provides OpenAI models adapted to their own binary format for download through Hugging Face.