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:
- 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”.
- 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!