Riva Client stops when sending 10,000 async requests

I have setup RIVA ASR on Jetson Orin successfully. I am using the python-client library https://github.com/nvidia-riva/python-clients/blob/main/tutorials/ASR.ipynb as a reference.
When I call offline_recognize with future=True, it works fine for 1,000 audio samples. But if I increase the samples to 10,000 the sockets gets closed, yielding the following error:

 File "/home/esraa_gad/.local/lib/python3.8/site-packages/grpc/_channel.py", line 881, in result
    raise self
grpc._channel._MultiThreadedRendezvous: <_MultiThreadedRendezvous of RPC that terminated with:
	status = StatusCode.UNAVAILABLE
	details = "Socket closed"
	debug_error_string = "UNKNOWN:Error received from peer  {grpc_message:"Socket closed", grpc_status:14, created_time:"2023-11-16T11:25:19.108859503+02:00"}"

When I try to use the docker again, to rest if the riva_asr_client is still working I get this response:

root@848871d0a303:/opt/riva# riva_asr_client --audio_file=/opt/riva/wav/ar-AR_sample.wav --language_code=ar-AR
I1115 22:50:13.598814   210 grpc.h:94] Using Insecure Server Credentials
Error creating GRPC channel: Unable to establish connection to server. Current state: 3
Exiting.
root@848871d0a303:/opt/riva#

I even try to stop and start the docker, but it yields the same response.

i am also attaching the output from docker logs riva-speechas logs.txt

Specs:
Hardware:Jetson Orin AGX
Operating System: Ubuntu
Riva Version: arm64_v2.13.1
Package: nvidia-jetpack
Version: 5.1-b147
Architecture: arm64
Maintainer: NVIDIA Corporation
Installed-Size: 194
Depends: nvidia-jetpack-runtime (= 5.1-b147), nvidia-jetpack-dev (= 5.1-b147)
GCC version: gcc version 9.3.0 (Buildroot 2020.08)
nvidia driver: version: 35.2.1

How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)
Run the tutorial code in https://github.com/nvidia-riva/python-clients/blob/main/tutorials/ASR.ipynb for async offline processing with 10,000 iterations.
logs.txt (88.3 KB)