暫無描述

Abandon-ht 5503f8d036 Update wave-reader.cc (#356) 11 月之前
.github f92325f041 Add Silero VAD version 4 (#353) 11 月之前
android ca9c19facd Add Android WearOS demo (#319) 1 年之前
c-api-examples 401de81194 Add hotwords support to Swift/Go/Python/C#/Kotlin APIs (#260) 1 年之前
cmake f92325f041 Add Silero VAD version 4 (#353) 11 月之前
dotnet-examples 77c34f3cff Add microphone example for .Net (#248) 2 年之前
ffmpeg-examples 0ba47330ce FFmpeg: Feed PCM to K2 direclty, without any buffer. (#183) 2 年之前
go-api-examples 343eab32ab Update sherpa-ncnn-go version (#245) 2 年之前
ios-swift b4260f7acf Refactor code (#163) 2 年之前
ios-swiftui f12aac47c3 Add SwiftUI demo project (#175) 2 年之前
mfc-examples 98ba3218db Fix MFC examples (#268) 1 年之前
nodejs-examples 41ebcfb11b Add WebAssembly + NodeJS example. (#311) 1 年之前
python-api-examples 87899c26fe Add Python ASR example with alsa (#324) 1 年之前
scripts 2e89994fc6 Fix building. (#325) 1 年之前
sherpa-ncnn 5503f8d036 Update wave-reader.cc (#356) 11 月之前
swift-api-examples f92325f041 Add Silero VAD version 4 (#353) 11 月之前
toolchains f9a850c725 Support RISC-V (#213) 2 年之前
wasm 41ebcfb11b Add WebAssembly + NodeJS example. (#311) 1 年之前
.clang-format 78ce6f6233 Add CI test and refactor the code a bit. (#4) 2 年之前
.gitignore 41ebcfb11b Add WebAssembly + NodeJS example. (#311) 1 年之前
CMakeLists.txt 87899c26fe Add Python ASR example with alsa (#324) 1 年之前
CPPLINT.cfg 78ce6f6233 Add CI test and refactor the code a bit. (#4) 2 年之前
LICENSE f91cd77f83 Use standard apache 2.0 license (#123) 2 年之前
MANIFEST.in 2b5300e975 Add Python API (#47) 2 年之前
README.md f92325f041 Add Silero VAD version 4 (#353) 11 月之前
build-aarch64-linux-gnu.sh 661b4e715c fix the version of alsa-lib (#348) 1 年之前
build-android-arm64-v8a-with-vulkan.sh 6b7072b3d9 Pack all sources into a single tar for embedded systems (#96) 2 年之前
build-android-arm64-v8a.sh 6b7072b3d9 Pack all sources into a single tar for embedded systems (#96) 2 年之前
build-android-armv7-eabi.sh 6b7072b3d9 Pack all sources into a single tar for embedded systems (#96) 2 年之前
build-android-x86-64.sh 6b7072b3d9 Pack all sources into a single tar for embedded systems (#96) 2 年之前
build-android-x86.sh 2878e796a5 build script for android-x86 (#228) 2 年之前
build-apk.sh fc4d3bc2d9 Rlease pre-built APK for English and French (#256) 1 年之前
build-arm-linux-gnueabihf.sh 661b4e715c fix the version of alsa-lib (#348) 1 年之前
build-ios.sh 7a5f80edc4 fix building for iOS (#92) 2 年之前
build-m3axpi.sh b701bc8daa Fix building on m3axpi (#99) 2 年之前
build-riscv64-linux-gnu.sh 661b4e715c fix the version of alsa-lib (#348) 1 年之前
build-swift-macos.sh f92325f041 Add Silero VAD version 4 (#353) 11 月之前
build-wasm-simd-for-nodejs.sh 41ebcfb11b Add WebAssembly + NodeJS example. (#311) 1 年之前
build-wasm-simd.sh 72ea103e9b Add WebAssembly (#300) 1 年之前
install-vulkan-macos.md d5dd41a7e2 Support building android app (#37) 2 年之前
pack-for-embedded-systems.sh 884ce6d9eb Use tencent/ncnn master. (#320) 1 年之前
release.sh 797f1e4243 Release pre-compiled libs for Android and iOS (#181) 2 年之前
setup.py df9ae1ff84 Publish to PyPI (#48) 2 年之前

README.md

Supported functions

Real-time Speech recognition Voice activity detection
✔️ ✔️

Supported platforms

Architecture Android iOS Windows macOS linux
x64 ✔️ ✔️ ✔️ ✔️
x86 ✔️ ✔️
arm64 ✔️ ✔️ ✔️ ✔️ ✔️
arm32 ✔️ ✔️
riscv64 ✔️

Supported programming languages

1. C++ 2. C 3. Python 4. JavaScript
✔️ ✔️ ✔️ ✔️
5. Go 6. C# 7. Kotlin 8. Swift
✔️ ✔️ ✔️ ✔️

It also supports WebAssembly.

Introduction

This repository supports running the following functions locally

  • Streaming speech-to-text (i.e., real-time speech recognition)
  • VAD (e.g., silero-vad)

on the following platforms and operating systems:

with the following APIs

  • C++, C, Python, Go, C#
  • Kotlin
  • JavaScript
  • Swift

We support all platforms that ncnn supports.

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

HINT: It does not depend on PyTorch or any other inference frameworks other than ncnn.

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:

Links for pre-built Android APKs

Description URL
Streaming speech recognition Address

Links for pre-trained models

https://github.com/k2-fsa/sherpa-ncnn/releases/tag/models

Useful links

How to reach us

Please see https://k2-fsa.github.io/sherpa/social-groups.html for 新一代 Kaldi 微信交流群 and QQ 交流群.

See also