FunASR本地docker离线环境cpu部署

1. docker拉取镜像registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.13

2. 运行镜像

sudo docker run -p 33005:10095 -it \
  --privileged=true \
  -v /mnt/inaisfs/funasr/models:/workspace/models \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.13

3. 进入运行的容器中，运行脚本

nohup bash run_server_2pass.sh \
  --model-dir /workspace/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
  --online-model-dir /workspace/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx \
  --punc-dir /workspace/models/iic/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx \
  --lm-dir /workspace/models/iic/speech_ngram_lm_zh-cn-ai-wesp-fst \
  --itn-dir /workspace/models/thuduj12/fst_itn_zh \
  --vad-dir /workspace/models/iic/speech_fsmn_vad_zh-cn-16k-common-onnx \
  --port 10095 \
  --certfile 0 > log_2pass.txt 2>&1 &

注意：运行的模型都应该在modelscope中先现在好