Error on Sample API Call

[usr-av]

I am running runtime-only chart and do not have minio setup, Is that required?

I am able to get models,
I get logs in cases where audio file is missing etc.
but no logs on runtime and bad gateway on HAP with sample audio file.

 curl --url "https://localhost:9443/speech-to-text/api/v1/recognize?model=en-US_Multimedia" \
      --insecure \
      --header "Content-Type: audio/flac" \
      --data-binary @example.flac

{
"error": "Bad Gateway. (HAP)",
"code": 502,
"code_description": "Bad Gateway"
}

pod logs
Runtime -

2023-09-07T07:44:26-04:00 "INFO: Will download the following models defined in group default in catalog b'var/catalog.json' : ['en-US_Multimedia', 'en-US_Telephony']"
2023-09-07T07:44:26-04:00 "INFO: All 6 models files extracted to modelDir /opt/ibm/chuck.x86_64/var/models"
2023-09-07T07:44:26-04:00 <2023-09-07 11:44:26,925 src/global.cc:28>	RD_INFO 	RAPID recognizer 5.4.0 (C) IBM Corp. 2015-2020 (git revision 4e52e03fe57718461388d29838b4d269bbd1fb91-modified                    )
2023-09-07T07:44:31-04:00 fatal: not a git repository (or any of the parent directories): .git
2023-09-07T07:44:31-04:00 fatal: not a git repository (or any of the parent directories): .git
2023-09-07T07:44:57-04:00 "INFO: Chuck server ready."

HAProxy

2023-09-07T08:04:00-04:00 <134>Sep  7 12:04:00 haproxy[482]: 127.0.0.1:51180 [07/Sep/2023:12:03:58.562] the-frontend~ the-backend/runtime 0/0/8/-1/1496 502 206 - - SH-- 1/1/0/0/0 0/0 {} "POST /speech-to-text/api/v1/recognize?model=en-US_Multimedia HTTP/1.1"