Speech-to-text-deployment notebook

Please provide the following information when requesting support.

Hardware - DGX Workstation
Operating System - Linux
Riva Version - Quick 1.4, as said in your notebook

How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)

follow instructions for riva2nemo → stt_de_citrinet_1024.riva

follow instructions from:

use notebook for “speech-to-text-deployment”

at the end when you try to start “riva_start.sh config.sh”:

Invalid argument: ensemble ‘riva-asr’ depends on ‘riva-asr-voice-activity-detector-ctc-streaming-offline’ which has no loaded version


UNAVAILABLE: Invalid argument: unable to find ‘libtriton_riva_asr_decoder_cpu.so’ for model 'riva-asr-ctc-decoder-cpu-stream, searched: /data/models/riva-asr-ctc-decoder-cpu-streaming-offline/1, /data/models/riva-asr-ctc-decoder-cpu-streaming-offline, /opt/tritonserver/backends/riva_asr_decoder_cpu

docker_log.txt (7.5 KB)

Could you please share the logs from riva-deploy?