README.md

Speech recognition with Next-gen Kaldi

This repo contains ncnn model files, which are converted from models trained using https://github.com/k2-fsa/icefall/pull/558 via pnnx.

The inference framework is https://github.com/k2-fsa/sherpa-ncnn

Usage

sudo apt-get install git-lfs
git lfs install

git clone https://huggingface.co/csukuangfj/sherpa-ncnn-2022-09-05

git clone https://github.com/k2-fsa/sherpa-ncnn
mkdir sherpa-ncnn/build
ln -s $PWD/sherpa-ncnn-2022-09-05/bar ./sherpa-ncnn/build
ln -s $PWD/sherpa-ncnn-2022-09-05/test_wavs ./sherpa-ncnn/build

cd sherpa-ncnn/build
cmake ..
make -j

./bin/sherpa-ncnn ./test_wavs/1089-134686-0001.wav

./bin/sherpa-ncnn ./test_wavs/1221-135766-0001.wav

./bin/sherpa-ncnn ./test_wavs/1221-135766-0002.wav

If you have any issues, please ask at https://github.com/k2-fsa/sherpa-ncnn/issues