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:2.6.0 exists. Skipping. > Image nvcr.io/nvidia/riva/riva-speech:2.6.0-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. /bin/bash: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8) ========================== === Riva Speech Skills === ========================== NVIDIA Release (build 45250447) Copyright (c) 2016-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. Copyright (c) 2018-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. https://developer.nvidia.com/tensorrt 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: https://developer.nvidia.com/ngc/nvidia-deep-learning-container-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 https://github.com/NVIDIA/TensorRT for more information. /bin/bash: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8) /data/artifacts /opt/riva Directory rmir_nlp_punctuation_bert_base_en_us_v2.6.0 already exists, skipping. Use '--force' option to override. /opt/riva Converting RMIRs at riva-model-repo/rmir to Riva Model repository. /bin/bash: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8) ========================== === Riva Speech Skills === ========================== NVIDIA Release (build 45250447) Copyright (c) 2016-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. Copyright (c) 2018-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. https://developer.nvidia.com/tensorrt 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: https://developer.nvidia.com/ngc/nvidia-deep-learning-container-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 https://github.com/NVIDIA/TensorRT for more information. /bin/bash: warning: setlocale: LC_ALL: cannot change locale (en_US.UTF-8) [NeMo W 2022-10-26 12:26:00 optimizers:55] Apex was not found. Using the lamb or fused_adam optimizer will error out. 2022-10-26 12:26:00,610 [INFO] Writing Riva model repository to '/data/models'... 2022-10-26 12:26:00,610 [INFO] The riva model repo target directory is /data/models 2022-10-26 12:26:09,480 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:09,480 [WARNING] /data/models/riva-trt-conformer-en-US-asr-offline-am-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-conformer-en-US-asr-offline-am-streaming-offline 2022-10-26 12:26:09,480 [WARNING] /data/models/conformer-en-US-asr-offline-feature-extractor-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-offline-feature-extractor-streaming-offline 2022-10-26 12:26:09,480 [WARNING] /data/models/conformer-en-US-asr-offline-endpointing-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-offline-endpointing-streaming-offline 2022-10-26 12:26:09,480 [WARNING] /data/models/conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-offline-ctc-decoder-cpu-streaming-offline 2022-10-26 12:26:09,480 [WARNING] /data/models/conformer-en-US-asr-offline already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-offline 2022-10-26 12:26:13,300 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:13,300 [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 2022-10-26 12:26:13,301 [WARNING] /data/models/text_classification_tokenizer-en-US-domain already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/text_classification_tokenizer-en-US-domain 2022-10-26 12:26:13,301 [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 2022-10-26 12:26:22,394 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:22,395 [WARNING] /data/models/riva-trt-riva-punctuation-en-US-nn-bert-base-uncased already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-riva-punctuation-en-US-nn-bert-base-uncased 2022-10-26 12:26:22,395 [WARNING] /data/models/riva-punctuation-en-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-punctuation-en-US 2022-10-26 12:26:26,464 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:26,464 [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 2022-10-26 12:26:26,464 [WARNING] /data/models/intent_slot_tokenizer-en-US-weather already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/intent_slot_tokenizer-en-US-weather 2022-10-26 12:26:26,464 [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 2022-10-26 12:26:26,464 [WARNING] /data/models/intent_slot_detokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/intent_slot_detokenizer 2022-10-26 12:26:26,464 [WARNING] /data/models/riva_intent_weather already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_intent_weather 2022-10-26 12:26:31,495 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:31,495 [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 2022-10-26 12:26:31,496 [WARNING] /data/models/qa_tokenizer-en-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/qa_tokenizer-en-US 2022-10-26 12:26:31,496 [WARNING] /data/models/qa_qa_postprocessor already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/qa_qa_postprocessor 2022-10-26 12:26:31,496 [WARNING] /data/models/riva_qa already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_qa 2022-10-26 12:26:40,406 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:40,407 [WARNING] /data/models/riva-trt-conformer-en-US-asr-streaming-am-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-conformer-en-US-asr-streaming-am-streaming 2022-10-26 12:26:40,407 [WARNING] /data/models/conformer-en-US-asr-streaming-feature-extractor-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-streaming-feature-extractor-streaming 2022-10-26 12:26:40,407 [WARNING] /data/models/conformer-en-US-asr-streaming-endpointing-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-streaming-endpointing-streaming 2022-10-26 12:26:40,407 [WARNING] /data/models/conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-streaming-ctc-decoder-cpu-streaming 2022-10-26 12:26:40,407 [WARNING] /data/models/conformer-en-US-asr-streaming already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/conformer-en-US-asr-streaming 2022-10-26 12:26:41,846 [INFO] Using onnx runtime 2022-10-26 12:26:41,847 [INFO] Using tensorrt with fp16 2022-10-26 12:26:41,847 [WARNING] /data/models/tts_preprocessor-English-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/tts_preprocessor-English-US 2022-10-26 12:26:41,847 [WARNING] /data/models/riva-onnx-fastpitch_encoder-English-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-onnx-fastpitch_encoder-English-US 2022-10-26 12:26:41,847 [WARNING] /data/models/spectrogram_chunker-English-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/spectrogram_chunker-English-US 2022-10-26 12:26:41,847 [WARNING] /data/models/riva-trt-hifigan-English-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva-trt-hifigan-English-US 2022-10-26 12:26:41,847 [WARNING] /data/models/tts_postprocessor-English-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/tts_postprocessor-English-US 2022-10-26 12:26:41,847 [WARNING] /data/models/fastpitch_hifigan_ensemble-English-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/fastpitch_hifigan_ensemble-English-US 2022-10-26 12:26:45,660 [INFO] Using obey-precision pass with fp16 TRT 2022-10-26 12:26:45,660 [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 2022-10-26 12:26:45,660 [WARNING] /data/models/token_classification_tokenizer-en-US already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/token_classification_tokenizer-en-US 2022-10-26 12:26:45,660 [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 2022-10-26 12:26:45,660 [WARNING] /data/models/token_classification_detokenizer already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/token_classification_detokenizer 2022-10-26 12:26:45,660 [WARNING] /data/models/riva_ner already exists, skipping deployment. To force deployment rerun with -f or remove the /data/models/riva_ner Riva initialization complete. Run ./riva_start.sh to launch services.