| ### Tutorial | |
| Start Server | |
| ``` | |
| docker pull soar97/triton-wenet:22.12 | |
| docker run -it --rm --name "wenet_tlg_test" --gpus all --shm-size 1g --net host soar97/triton-wenet:22.12 | |
| git-lfs install | |
| git clone https://huggingface.co/yuekai/model_repo_conformer_aishell_wenet_tlg.git | |
| cd model_repo_conformer_aishell_wenet_tlg | |
| bash run.sh | |
| ``` | |
| Start Client | |
| ``` | |
| pip3 install tritonclient[all]==2.29 | |
| apt-get install -y libsndfile1 | |
| pip3 install soundfile | |
| python3 generate_perf_input.py --audio_file ./mid.wav | |
| perf_analyzer -m attention_rescoring -b 1 -p 20000 --concurrency-range 100 -i gRPC --input-data=offline_input.json -u localhost:8001 | |
| ``` | |