#Which model for streaming conversations about stock companies?

1 messages · Page 1 of 1 (latest)

sand glacier
#

Hi there,

I’ve been testing the streaming speech to text API - and it’s very good so far. But I just saw you have a few “finance” models - one for Nova-2, Enhanced and Base; and I see they are designed for “vocabulary that is heavily finance oriented”.

Couple questions:

  1. Are they trained on all the stock market company names? For example I heard someone say “Leidos Holdings”, but the Nova-2 General model caught it as “lei this”.
  2. I saw you can use keywords to assist, but there are like 3000 (relevant) company names., and it seems to be limited to 50. Any other ways to help with detection?

The Nova-2 Generalmodel already catches more common company names like Netflix, Microsoft, etc. but I’m looking for greater accuracy amongst more obscure company names.

Thanks!

sand spearBOT
#

Thanks for asking your question. Please be sure to reply with as much detail as possible so we can assist you efficiently. Such as:

  • Provide the request_id if you've a question about a transcription response.
  • The options you used or the api.deepgram.com URL you sent your request to, including parameters.
  • Any code snippets you can include.
  • Any audio you can include, or if you can't share it here please email it to us at [email protected] and provide a link to this thread.
tidal wren
#

If you'd like to achieve greater accuracy you can try our keywords feature, but it has a greater impact on base models over nova models.

If that isn't enough, we do offer enterprise customers custom model training.

sand glacier