Riva deployement error with custom ngram langugae model and custom acoustic model

AI & Data Science Deep Learning (Training & Inference) Riva
1

Hello,

I have been facing this issue when I try to deploy riva with custom n-gram language model and acoustic model.

Hardware - NVIDIA RTX A5000
Hardware - GPU
Operating System: Ubuntu: 20.04.3 LTS
Riva Version 2.9.0.

I0607 12:05:02.027920 108 ctc-decoder-library.cc:23] TRITONBACKEND_ModelInstanceInitialize: offline_riva_ngram_lm_pipeline-ctc-decoder-cpu-streaming-offline_0 (device 0)
terminate called after throwing an instance of ‘std::invalid_argument’
what(): Unknown entry in dictionary: ‘<’
/opt/riva/bin/start-riva: line 4: 108 Aborted (core dumped) ${CUSTOM_TRITON_ENV} tritonserver --log-verbose=0 --strict-model-config=true $model_repos --cuda-memory-pool-byte-size=0:1000000000