sherpa-ncnn

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

APACHE-2.0 License

Downloads
17.5K
Stars
997
Committers
7
View Code on GitHub Visit Website
Ecosystems: C#, Kotlin, C++, C, Go, Python

Bot releases are hidden (Show)

sherpa-ncnn - Release v1.5.2

Published by csukuangfj over 1 year ago

small fixes

sherpa-ncnn - Release v1.5.1

Published by csukuangfj over 1 year ago

Bugfixes

sherpa-ncnn - Release v1.5.0

Published by csukuangfj over 1 year ago

Support streaming zipformer

sherpa-ncnn - Release v1.4.3

Published by csukuangfj over 1 year ago

sherpa-ncnn - Release v1.4.2

Published by csukuangfj over 1 year ago

  • Optimize modified_beam_search
sherpa-ncnn - v1.4.1

Published by csukuangfj over 1 year ago

sherpa-ncnn - Release v1.4.0

Published by csukuangfj over 1 year ago

  • Support iOS
  • Support Android
sherpa-ncnn - Release v1.3.2

Published by csukuangfj almost 2 years ago

Fix endpointing bug in #66

sherpa-ncnn - Release v1.3.1

Published by csukuangfj almost 2 years ago

  • optimize modified_beam_search
  • more verbose output on failing to create a model
sherpa-ncnn - Release v1.0

Published by csukuangfj almost 2 years ago

Package Rankings
Top 23.67% on Npmjs.org
Top 8.2% on Pypi.org
Top 9.78% on Proxy.golang.org
Related Projects
kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

20 Apr 2015 14,165
sherpa-onnx

Speech-to-text, text-to-speech, speaker recognition, and VAD using next-gen Kaldi with onnxruntim...

01 Sep 2022 3,055
TensorVox

Desktop application for neural speech synthesis written in C++

13 Aug 2020 197