This repository has been archived on 2025-08-26. You can view files and clone it, but cannot push or open issues or pull requests.
Fangjun Kuang a0a0882419 small fixes
2022-10-12 11:28:39 +08:00
2022-10-12 11:28:39 +08:00
2022-10-12 11:27:05 +08:00
2022-09-02 20:29:07 +08:00

Introduction

See https://github.com/k2-fsa/sherpa

This repo uses onnxruntime and does not depend on libtorch.

Onnxruntime Installation

git clone --recursive --branch v1.12.1 https://github.com/Microsoft/onnxruntime
cd onnxruntime
./build.sh \
    --config RelWithDebInfo \
    --build_shared_lib \
    --build_wheel \
    --skip_tests \
    --parallel 16
cd build/Linux/RelWithDebInfo
sudo make install
export LD_LIBRARY_PATH=/path/to/onnxruntime/build/Linux/RelWithDebInfo:$LD_LIBRARY_PATH

Usage

git clone https://github.com/k2-fsa/sherpa-onnx
cd sherpa-onnx
mkdir build
cd build
cmake -DONNXRUNTIME_ROOTDIR=/path/to/onnxruntime \
      -DKALDI_NATIVE_IO_INSTALL_PREFIX=/path/to/kaldi_native_io ..
make
./bin/sherpa-onnx path/to/encoder.onnx \
                  path/to/decoder.onnx \
                  path/to/joiner.onnx \
                  path/to/joiner_encoder_proj.onnx \
                  path/to/joiner_decoder_proj.onnx \
                  path/to/tokens.txt \
                  greedy \
                  path/to/audio.wav
Description
*此项目已归档,勿使用*
Readme Apache-2.0 35 MiB
Languages
C++ 38.3%
Python 16.3%
Shell 7.6%
Kotlin 5.1%
JavaScript 5.1%
Other 27.4%