DeepLearningExamples icon indicating copy to clipboard operation
DeepLearningExamples copied to clipboard

[Kaldi/SpeechRecognition] can't access grpc server of gpu-decode by python client.

Open LearnMF opened this issue 2 years ago • 0 comments

Related to Kaldi/SpeechRecognition (notebooks/Kaldi_TRTIS_inference_online_demo.ipynb

Describe the bug When I try to connect triton grpc server by python client, i found i can't get access! The blow is error info:

_InactiveRpcError Traceback (most recent call last) in 7 request = grpc_service_pb2.StatusRequest(model_name=FLAGS.model_name) 8 # Call and receive response from Status gRPC ----> 9 response = grpc_stub.Status(request) 10 11 print(response)

/usr/local/lib/python3.8/dist-packages/grpc/_channel.py in call(self, request, timeout, metadata, credentials, wait_for_ready, compression) 944 state, call, = self._blocking(request, timeout, metadata, credentials, 945 wait_for_ready, compression) --> 946 return _end_unary_response_blocking(state, call, False, None) 947 948 def with_call(self,

/usr/local/lib/python3.8/dist-packages/grpc/_channel.py in _end_unary_response_blocking(state, call, with_call, deadline) 847 return state.response 848 else: --> 849 raise _InactiveRpcError(state) 850 851

_InactiveRpcError: <_InactiveRpcError of RPC that terminated with: status = StatusCode.UNIMPLEMENTED details = "" debug_error_string = "{"created":"@1668144039.054077211","description":"Error received from peer ipv4:127.0.0.1:8001","file":"src/core/lib/surface/call.cc","file_line":1067,"grpc_message":"","grpc_status":12}"

To Reproduce Steps to reproduce the behavior:

  1. I start the gpu-kaldi server in a container, and then i execute cpp client(offered in repository);the client and server work well,i also get the expected response, but when i switch the Kaldi_TRTIS_inference_online_demo.ipynb ,it failed to connect the server.

Below is what i thought about this question: the tensorrtserver used in Kaldi_TRTIS_inference_online_demo.ipynb is installed by myself, with the cammand "pip install tensorrtserver"; and the version is 1.11.0; then i run the jupyter step by step until the error occurred. i google some similar error, i also tryed unset proxy, but it didn't work; i wish to get some help thx andvance

Environment Please provide at least:

  • Container version :21.05-py3-sdk
  • GPUs in the system: :Tesla T4
  • CUDA driver version :470.103.01

LearnMF avatar Nov 11 '22 05:11 LearnMF