Skip to content

❓ How to setup max speech duration? #42

Answered by snakers4
garymmi asked this question in Q&A
Discussion options

You must be logged in to vote

Hi,

Have you checked, is this really long non-stop speech (or two people talking together) and not some wrong hyper-parameter choice?

In case of really long speech there is no clear obvious solution.
Because from a standpoint of our VAD the speech does not really end.

Together with STT a proper solution would be:

  • Find a long speech chunk;
  • Just divide in into N equal parts (or into N-second chunks);
  • Get timestamps of words in each chunk;
  • Re-cut chunks not to cut any words "in the middle";

Replies: 2 comments

Comment options

You must be logged in to vote
0 replies
Answer selected by snakers4
Comment options

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants
Converted from issue

This discussion was converted from issue #41 on March 11, 2021 10:03.