Тайлбар байхгүй

Fangjun Kuang 9735f120c6 Update readme (#39) 2 жил өмнө
.github 491c7b99b4 Support building for android (#35) 2 жил өмнө
android d5dd41a7e2 Support building android app (#37) 2 жил өмнө
cmake d5dd41a7e2 Support building android app (#37) 2 жил өмнө
scripts 78ce6f6233 Add CI test and refactor the code a bit. (#4) 2 жил өмнө
sherpa-ncnn d5dd41a7e2 Support building android app (#37) 2 жил өмнө
toolchains 767e37f6cf Support building for aarch64 (#7) 2 жил өмнө
.clang-format 78ce6f6233 Add CI test and refactor the code a bit. (#4) 2 жил өмнө
.gitignore 0e5a58da20 add arm build support (#3) 2 жил өмнө
CMakeLists.txt 491c7b99b4 Support building for android (#35) 2 жил өмнө
CPPLINT.cfg 78ce6f6233 Add CI test and refactor the code a bit. (#4) 2 жил өмнө
LICENSE 3185205428 First commit 2 жил өмнө
README.md 9735f120c6 Update readme (#39) 2 жил өмнө
build-aarch64-linux-gnu.sh f1add11491 Small fixes to the cross-compiling scripts (#38) 2 жил өмнө
build-android-arm64-v8a-with-vulkan.sh f1add11491 Small fixes to the cross-compiling scripts (#38) 2 жил өмнө
build-android-arm64-v8a.sh d5dd41a7e2 Support building android app (#37) 2 жил өмнө
build-android-armv7-eabi.sh d5dd41a7e2 Support building android app (#37) 2 жил өмнө
build-android-x86-64.sh d5dd41a7e2 Support building android app (#37) 2 жил өмнө
build-arm-linux-gnueabihf.sh f1add11491 Small fixes to the cross-compiling scripts (#38) 2 жил өмнө
install-vulkan-macos.md d5dd41a7e2 Support building android app (#37) 2 жил өмнө

README.md

Introduction

You can use sherpa-ncnn for real-time speech recognition (i.e., speech-to-text) on

  • Linux
  • macOS
  • Windows
  • Embedded Linux (32-bit arm and 64-bit aarch64)
  • Android
  • etc ...

We support all platforms that ncnn supports.

Everything can be compiled from source with static link. The generated executable depends only on system libraries.

Please see the documentation https://k2-fsa.github.io/sherpa/ncnn/index.html for installation and usages, e.g.,

  • How to build an Android app
  • How to download and use pre-trained models

We provide a few YouTube videos for demonstration about real-time speech recognition with sherpa-ncnn using a microphone:

Note: If you don't have access to YouTube, we provide the links in bilibili below:

See also https://github.com/k2-fsa/sherpa