search

NVIDIA / DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
13.47k stars 3.21k forks source link

Tried with Kaldi-ASR demo, no result comes back #653

Open jackyh opened 4 years ago

jackyh commented 4 years ago

I followed the steps https://github.com/NVIDIA/DeepLearningExamples/tree/master/Kaldi/SpeechRecognition. After Server started, I start the client with: scripts/docker/launch_client.sh -p -v. The client says: Loading eval dataset...done Opening GRPC contextes...done Streaming utterances...Sending correlation_id=1 chunk offset=8160 Sending correlation_id=2 chunk offset=8160 Sending correlation_id=3 chunk offset=8160 Sending correlation_id=4 chunk offset=8160 .... But, it will stopped at "Waiting for all results...", and no results comes back. Why? Do I need to do anything else?

jackyh commented 4 years ago

I tried to use " tcpdump tcp port 8001 -vv", look like when client started, no GPRC request is sent out? Is there any step that I'm missing?