Fangjun Kuang
0a65dbe30a
Fix inner product output shape for arm (#12)
|
há 2 anos atrás | |
|---|---|---|
| .github | há 2 anos atrás | |
| cmake | há 2 anos atrás | |
| scripts | há 2 anos atrás | |
| sherpa-ncnn | há 2 anos atrás | |
| toolchains | há 2 anos atrás | |
| .clang-format | há 2 anos atrás | |
| .gitignore | há 2 anos atrás | |
| CMakeLists.txt | há 2 anos atrás | |
| CPPLINT.cfg | há 2 anos atrás | |
| LICENSE | há 2 anos atrás | |
| README.md | há 2 anos atrás | |
| build-aarch64-linux-gnu.sh | há 2 anos atrás | |
| build-arm-linux-gnueabihf.sh | há 2 anos atrás |
README.md
Introduction
Documentation: https://k2-fsa.github.io/sherpa/ncnn/index.html
See https://github.com/k2-fsa/sherpa
This repo uses ncnn for running the neural network model and does not depend on libtorch.
Please read https://k2-fsa.github.io/icefall/recipes/librispeech/lstm_pruned_stateless_transducer.html if you are interested in how the model is trained.
We provide exported models in ncnn format and they can be downloaded using the following links:
- English: https://huggingface.co/csukuangfj/sherpa-ncnn-2022-09-05
- Chinese: (TODO, We will provide it soon)
Usage
git clone https://github.com/k2-fsa/sherpa-ncnn
cd sherpa-ncnn
mkdir build
cd build
cmake ..
make -j6
cd ..
# Now download the pretrained model
git lfs install
git clone https://huggingface.co/csukuangfj/sherpa-ncnn-2022-09-05
./build/bin/sherpa-ncnn \
./sherpa-ncnn-2022-09-05/tokens.txt \
./sherpa-ncnn-2022-09-05/bar/encoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.param \
./sherpa-ncnn-2022-09-05/bar/encoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.bin \
./sherpa-ncnn-2022-09-05/bar/decoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.param \
./sherpa-ncnn-2022-09-05/bar/decoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.bin \
./sherpa-ncnn-2022-09-05/bar/joiner_jit_trace-iter-468000-avg-16-pnnx.ncnn.param \
./sherpa-ncnn-2022-09-05/bar/joiner_jit_trace-iter-468000-avg-16-pnnx.ncnn.bin \
./sherpa-ncnn-2022-09-05/test_wavs/1089-134686-0001.wav
To do speech recognition in real-time with a microphone, run:
./build/bin/sherpa-ncnn-microphone \
./sherpa-ncnn-2022-09-05/tokens.txt \
./sherpa-ncnn-2022-09-05/bar/encoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.param \
./sherpa-ncnn-2022-09-05/bar/encoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.bin \
./sherpa-ncnn-2022-09-05/bar/decoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.param \
./sherpa-ncnn-2022-09-05/bar/decoder_jit_trace-iter-468000-avg-16-pnnx.ncnn.bin \
./sherpa-ncnn-2022-09-05/bar/joiner_jit_trace-iter-468000-avg-16-pnnx.ncnn.param \
./sherpa-ncnn-2022-09-05/bar/joiner_jit_trace-iter-468000-avg-16-pnnx.ncnn.bin \