speech-to-text improvements

[tkirill08]

Good afternoon!

I am a user of Speech-to-Text. I use it in order to get a written text from the interviews and courses I shoot myself. After that I correct the text manually.

So, in Russian it works fine, however, 30-40 percents of the words are incorrect. Moreover, there are no Russian punctuation at all.  So I get the speech-to-text transcript, then I create the perfect transcript out of this with correct words and punctuations.

All I want to know is how I can improve Speech-to-Text by using the perfect transcript I have already corrected? Where I can send that data to?

P.S. Sorry for my English. I hope You can understand me 🙂