-
Notifications
You must be signed in to change notification settings - Fork 1.6k
Closed
Labels
api: speechIssues related to the Speech-to-Text API.Issues related to the Speech-to-Text API.type: questionRequest for information or clarification. Not an issue.Request for information or clarification. Not an issue.
Description
The function sync_recognize() of the Speech API has consistently a shorter runtime, if I use a flac audio file with a sampling rate of 48 kHz in comparison to a sampling rate of 16 kHz.
How does it come that the larger file with more information to process, is analyzed faster?
And as a follow-up question: The docs say that a sampling rate of 16 kHz yields the best results. What is the reason for that?
(I already asked the question on Stack Overflow with some code included, but got no answer so far.)
Metadata
Metadata
Assignees
Labels
api: speechIssues related to the Speech-to-Text API.Issues related to the Speech-to-Text API.type: questionRequest for information or clarification. Not an issue.Request for information or clarification. Not an issue.