Sen descrición

Fangjun Kuang df9ae1ff84 Publish to PyPI (#48) %!s(int64=2) %!d(string=hai) anos
.github df9ae1ff84 Publish to PyPI (#48) %!s(int64=2) %!d(string=hai) anos
android d5dd41a7e2 Support building android app (#37) %!s(int64=2) %!d(string=hai) anos
cmake df9ae1ff84 Publish to PyPI (#48) %!s(int64=2) %!d(string=hai) anos
scripts 78ce6f6233 Add CI test and refactor the code a bit. (#4) %!s(int64=2) %!d(string=hai) anos
sherpa-ncnn df9ae1ff84 Publish to PyPI (#48) %!s(int64=2) %!d(string=hai) anos
toolchains 767e37f6cf Support building for aarch64 (#7) %!s(int64=2) %!d(string=hai) anos
.clang-format 78ce6f6233 Add CI test and refactor the code a bit. (#4) %!s(int64=2) %!d(string=hai) anos
.gitignore 2b5300e975 Add Python API (#47) %!s(int64=2) %!d(string=hai) anos
CMakeLists.txt df9ae1ff84 Publish to PyPI (#48) %!s(int64=2) %!d(string=hai) anos
CPPLINT.cfg 78ce6f6233 Add CI test and refactor the code a bit. (#4) %!s(int64=2) %!d(string=hai) anos
LICENSE 3185205428 First commit %!s(int64=2) %!d(string=hai) anos
MANIFEST.in 2b5300e975 Add Python API (#47) %!s(int64=2) %!d(string=hai) anos
README.md 9735f120c6 Update readme (#39) %!s(int64=2) %!d(string=hai) anos
build-aarch64-linux-gnu.sh f1add11491 Small fixes to the cross-compiling scripts (#38) %!s(int64=2) %!d(string=hai) anos
build-android-arm64-v8a-with-vulkan.sh a0d01e19da update to the latest master of ncnn (#43) %!s(int64=2) %!d(string=hai) anos
build-android-arm64-v8a.sh d5dd41a7e2 Support building android app (#37) %!s(int64=2) %!d(string=hai) anos
build-android-armv7-eabi.sh d5dd41a7e2 Support building android app (#37) %!s(int64=2) %!d(string=hai) anos
build-android-x86-64.sh d5dd41a7e2 Support building android app (#37) %!s(int64=2) %!d(string=hai) anos
build-arm-linux-gnueabihf.sh f1add11491 Small fixes to the cross-compiling scripts (#38) %!s(int64=2) %!d(string=hai) anos
install-vulkan-macos.md d5dd41a7e2 Support building android app (#37) %!s(int64=2) %!d(string=hai) anos
setup.py df9ae1ff84 Publish to PyPI (#48) %!s(int64=2) %!d(string=hai) anos

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