aws-samples / whisper-audio-inference-for-amazon-sagemaker Goto Github PK

Hi,

Getting an error in whisper_endpoin.predict()

In logs, I see the following

2023-04-09T13:29:53.758-07:00

2023-04-09T20:29:53,737 [ERROR] Thread-1151 org.pytorch.serve.metrics.MetricCollector - Traceback (most recent call last):
File "ts/metrics/metric_collector.py", line 27, in
system_metrics.collect_all(sys.modules['ts.metrics.system_metrics'], arguments.gpu)
File "/opt/conda/lib/python3.8/site-packages/ts/metrics/system_metrics.py", line 91, in collect_all
value(num_of_gpu)
File "/opt/conda/lib/python3.8/site-packages/ts/metrics/system_metrics.py", line 61, in gpu_utilization
import nvgpu

ModuleNotFoundError: No module named 'nvgpu'

W-9000-model_1.0 org.pytorch.serve.wlm.WorkerThread - Backend worker error

There are quite a few warning of worker thread dead but nothing else that warrants attention.

Followed all the steps... not sure what I missed. Any thoughts, what I may be missing?

FileNotFoundError: [Errno 2] No such file or directory: 'src'