|
il y a 1 an | |
---|---|---|
.. | ||
.gitignore | il y a 2 ans | |
README.md | il y a 2 ans | |
generate.py | il y a 2 ans | |
notes.md | il y a 2 ans | |
requirements.txt | il y a 2 ans | |
run.sh | il y a 2 ans | |
sherpa-ncnn.cs | il y a 1 an | |
sherpa-ncnn.csproj.in | il y a 2 ans | |
sherpa-ncnn.csproj.runtime.in | il y a 2 ans |
sherpa-ncnn is an open-source real-time speech recognition toolkit developed by the Next-gen Kaldi team.
It supports streaming recognition on a variety of platforms such as Android, iOS, Raspberry, Linux, Windows, macOS, etc.
It does not require Internet connection during recognition.
See the documentation https://k2-fsa.github.io/sherpa/ncnn/index.html for details.