nova-2 occasional duplicates, bad time stamps and missing sections

[willw1]

nova-2 has generally done an extremely good job on the Spanish prerecorded audio I have uploaded. However, it occasionally duplicates words and phrases and gives incorrect timestamps. As an example, in the audio file here, the section from 375.69998 to 387.72498 is transcribed as:

Acuérdate de que hoy tiene que estar listo el informe de ventas de la campaña de invierno. Lo tengo prácticamente finiquitado. Confío en ti. Por cierto, hemos quedado un prácticamente finiquitado. Confío en ti. Por cierto, hemos quedado unos cuantos para unas cañas a la salida del curro, ¿cómo os apuntáis?

The words in bold are incorrect duplicates which do not appear in the audio. Other examples: the section from 743.905 is repeated again starting at 747.41437, and most of the audio from 319.62 to 353.755 is not transcribed at all.

The request_id was 4f256cba-85d1-4759-8c64-9b51369671ee and I made the request using fetch in javascript. The transcript returned is attached to this message.

EL_HACKEO_Part1_transcript.json

[deepgram-community[bot]]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
_{Consider joining our Discord community for more opportunity to engage with your fellow Deepgram users. You can earn points which can be redeemed for cool stuff by being active in our communities!}

[deepgram-community[bot]]

Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion.