Timeout errors / Incorrect Language detection

[spare cape]

We are currently testing Speech-to-text transcription using the Deepgram API and we have encountered the following issues:
Significant processing delays: 3 to 5 minutes for audio files under 7 minutes in length.
Timeout errors on certain requests.
Incorrect language detection: for example, an audio file in French was transcribed in Turkish

We would appreciate any clarification regarding these issues and would like to know if there are recommended configurations or optimizations to improve performance.

Programming language: JavaScript
request ID that triggered is : 178e0636-a5ea-44d1-a891-5b6869ab729a

Thank you in advance for your support.

[fast scroll]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
-# If you haven't done so, ensure your Discord and Github profiles are linked to Deepgram so you can earn points to redeem on cool stuff just by being active!

[hybrid skiff]

I noticed you used Whisper in this request.

We recommend you use a Deepgram Model instead. Our instance of the Whisper model is pretty sub par for most needs and many people have challenges with it, especially around processing time.

 "model":"whisper-large"
 "diarize":"true"
 "smart_format":"true"
"detect_language":[
     0:"true"
            ]
"paragraphs":"true"
}```