Can´t start riva

I can´t run RIVA service after i run the init script. Did anyone see an issue in the init log file, please?

After i run the init script, service can´t start:
Starting Riva Speech Services. This may take several minutes depending on the number of models deployed.

c500a9152428b5acaf04f1ab2b6224d42d9a75dd8b290873d81e3172856462aa

Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds
Waiting for Riva server to load all models…retrying in 10 seconds

Please provide the following information when requesting support.

Hardware - RTX 3090, CUDA 11.6
Hardware - CPU Dual XEON 3.4 GHZ x86/64
Operating System: Ubuntu 18.04

Riva Version 1.10. Beta
Logging into NGC docker registry if necessary…
Pulling required docker images if necessary…
Note: This may take some time, depending on the speed of your Internet connection.

Pulling Riva Speech Server images.
Image nvcr.io/nvidia/riva/riva-speech:1.10.0-beta-server exists. Skipping.
Image nvcr.io/nvidia/riva/riva-speech-client:1.10.0-beta exists. Skipping.
Image nvcr.io/nvidia/riva/riva-speech:1.10.0-beta-servicemaker exists. Skipping.

Downloading models (RMIRs) from NGC…
Note: this may take some time, depending on the speed of your Internet connection.
To skip this process and use existing RMIRs set the location and corresponding flag in config.sh.

==========================
=== Riva Speech Skills ===

NVIDIA Release 22.02 (build 32720918)
Riva Speech Server Version 1.10.0-beta
Copyright (c) 2016-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2018-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:

To install Python sample dependencies, run /opt/tensorrt/python/python_setup.sh

To install the open-source samples corresponding to this TensorRT release version
run /opt/tensorrt/install_opensource.sh. To build the open source parsers,
plugins, and samples for current top-of-tree on master or a different branch,
run /opt/tensorrt/install_opensource.sh -b
See GitHub - NVIDIA/TensorRT: TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators. for more information.

/data/artifacts /opt/riva
Directory rmir_asr_citrinet_1024_en_us_str_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_asr_citrinet_1024_en_us_ofl_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_nlp_punctuation_bert_base_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_nlp_punctuation_bert_base_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_nlp_named_entity_recognition_bert_base_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_nlp_intent_slot_bert_base_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_nlp_question_answering_bert_base_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_nlp_text_classification_bert_base_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
Directory rmir_tts_fastpitch_hifigan_ljspeech_v1.10.0-beta already exists, skipping. Use ‘–force’ option to override.
/opt/riva

Converting RMIRs at riva-model-repo/rmir to Riva Model repository.

==========================
=== Riva Speech Skills ===

NVIDIA Release 22.02 (build 32720918)
Riva Speech Server Version 1.10.0-beta
Copyright (c) 2016-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

Copyright (c) 2018-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:

To install Python sample dependencies, run /opt/tensorrt/python/python_setup.sh

To install the open-source samples corresponding to this TensorRT release version
run /opt/tensorrt/install_opensource.sh. To build the open source parsers,
plugins, and samples for current top-of-tree on master or a different branch,
run /opt/tensorrt/install_opensource.sh -b
See GitHub - NVIDIA/TensorRT: TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators. for more information.

2022-04-03 08:32:16,783 [INFO] Writing Riva model repository to ‘/data/models’…
2022-04-03 08:32:16,783 [INFO] The riva model repo target directory is /data/models
2022-04-03 08:32:22,060 [INFO] Using tensorrt
2022-04-03 08:32:22,061 [WARNING] /data/models/riva-trt-citrinet-1024-en-US-asr-offline-am-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-citrinet-1024-en-US-asr-offline-am-streaming-offline
2022-04-03 08:32:22,061 [WARNING] /data/models/citrinet-1024-en-US-asr-offline-feature-extractor-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-offline-feature-extractor-streaming-offline
2022-04-03 08:32:22,061 [WARNING] /data/models/citrinet-1024-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-offline-voice-activity-detector-ctc-streaming-offline
2022-04-03 08:32:22,061 [WARNING] /data/models/citrinet-1024-en-US-asr-offline-ctc-decoder-cpu-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-offline-ctc-decoder-cpu-streaming-offline
2022-04-03 08:32:22,061 [WARNING] /data/models/citrinet-1024-en-US-asr-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-offline
2022-04-03 08:32:27,400 [INFO] Using tensorrt
2022-04-03 08:32:27,401 [WARNING] /data/models/riva-trt-citrinet-1024-en-US-asr-streaming-am-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-citrinet-1024-en-US-asr-streaming-am-streaming
2022-04-03 08:32:27,401 [WARNING] /data/models/citrinet-1024-en-US-asr-streaming-feature-extractor-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-streaming-feature-extractor-streaming
2022-04-03 08:32:27,401 [WARNING] /data/models/citrinet-1024-en-US-asr-streaming-voice-activity-detector-ctc-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-streaming-voice-activity-detector-ctc-streaming
2022-04-03 08:32:27,401 [WARNING] /data/models/citrinet-1024-en-US-asr-streaming-ctc-decoder-cpu-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-streaming-ctc-decoder-cpu-streaming
2022-04-03 08:32:27,401 [WARNING] /data/models/citrinet-1024-en-US-asr-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/citrinet-1024-en-US-asr-streaming
2022-04-03 08:32:30,720 [WARNING] /data/models/riva-trt-riva_punctuation-nn-bert-base-uncased already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-riva_punctuation-nn-bert-base-uncased
2022-04-03 08:32:30,721 [WARNING] /data/models/punctuation_tokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/punctuation_tokenizer
2022-04-03 08:32:30,721 [WARNING] /data/models/punctuation_punctuation_postprocessor already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/punctuation_punctuation_postprocessor
2022-04-03 08:32:30,721 [WARNING] /data/models/riva_punctuation already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_punctuation
2022-04-03 08:32:34,088 [WARNING] /data/models/riva-trt-riva_intent_weather-nn-bert-base-uncased already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-riva_intent_weather-nn-bert-base-uncased
2022-04-03 08:32:34,088 [WARNING] /data/models/intent_slot_tokenizer_weather already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/intent_slot_tokenizer_weather
2022-04-03 08:32:34,088 [WARNING] /data/models/intent_slot_label_tokens_weather already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/intent_slot_label_tokens_weather
2022-04-03 08:32:34,088 [WARNING] /data/models/intent_slot_detokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/intent_slot_detokenizer
2022-04-03 08:32:34,088 [WARNING] /data/models/riva_intent_weather already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_intent_weather
2022-04-03 08:32:36,802 [WARNING] /data/models/tts_preprocessor-ljspeech already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/tts_preprocessor-ljspeech
2022-04-03 08:32:36,802 [WARNING] /data/models/riva-onnx-fastpitch_encoder-ljspeech already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-onnx-fastpitch_encoder-ljspeech
2022-04-03 08:32:36,802 [WARNING] /data/models/spectrogram_chunker-ljspeech already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/spectrogram_chunker-ljspeech
2022-04-03 08:32:36,802 [WARNING] /data/models/riva-trt-hifigan-ljspeech already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-hifigan-ljspeech
2022-04-03 08:32:36,802 [WARNING] /data/models/tts_postprocessor-ljspeech already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/tts_postprocessor-ljspeech
2022-04-03 08:32:36,802 [WARNING] /data/models/fastpitch_hifigan_ensemble-ljspeech already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/fastpitch_hifigan_ensemble-ljspeech
2022-04-03 08:32:40,093 [WARNING] /data/models/riva-trt-riva_text_classification_domain-nn-bert-base-uncased already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-riva_text_classification_domain-nn-bert-base-uncased
2022-04-03 08:32:40,093 [WARNING] /data/models/text_classification_tokenizer_domain already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/text_classification_tokenizer_domain
2022-04-03 08:32:40,093 [WARNING] /data/models/riva_text_classification_domain already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_text_classification_domain
2022-04-03 08:32:43,447 [WARNING] /data/models/riva-trt-riva_ner-nn-bert-base-uncased already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-riva_ner-nn-bert-base-uncased
2022-04-03 08:32:43,447 [WARNING] /data/models/token_classification_tokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/token_classification_tokenizer
2022-04-03 08:32:43,447 [WARNING] /data/models/token_classification_label_tokens already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/token_classification_label_tokens
2022-04-03 08:32:43,447 [WARNING] /data/models/token_classification_detokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/token_classification_detokenizer
2022-04-03 08:32:43,447 [WARNING] /data/models/riva_ner already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_ner
2022-04-03 08:32:46,788 [WARNING] /data/models/riva-trt-riva_qa-nn-bert-base-uncased already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-riva_qa-nn-bert-base-uncased
2022-04-03 08:32:46,788 [WARNING] /data/models/qa_tokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/qa_tokenizer
2022-04-03 08:32:46,788 [WARNING] /data/models/qa_qa_postprocessor already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/qa_qa_postprocessor
2022-04-03 08:32:46,789 [WARNING] /data/models/riva_qa already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_qa

Riva initialization complete. Run ./riva_start.sh to launch services.

1 Like

Hi @rebotnix

Thanks for your interest in riva,

Apologies you were not able to run,

I find the provided riva_start.sh and riva_init.sh logs, regarding riva_start.sh, just want to check is it the full log

Also generally the riva_init.sh and riva_start.sh would take good amount of time to get ready (depending upon your config in config.sh and GPU, System etc.)

Can you once try running,

  • bash riva_clean.sh
  • bash riva_init.sh
  • bash riva_start.sh

and let us know whether it works, also it would be appreciated if you attach the logs as files during the above trial