KnowBrainer Speech Recognition
Decrease font size
Increase font size
Topic Title: ATFA - delay start of transcription process possible?
Topic Summary:
Created On: 09/15/2021 03:45 PM
Status: Post and Reply
Linear : Threading : Single : Branch
 ATFA - delay start of transcription process possible?   - marc_vie - 09/15/2021 03:45 PM  
 ATFA - delay start of transcription process possible?   - R. Wilke - 09/15/2021 04:18 PM  
 09/15/2021 03:45 PM
User is offline View Users Profile Print this message

Author Icon
Power Member

Posts: 54
Joined: 07/01/2014

I use ONLY the Auto Transcribe Folder Agent (ATFA in DMPE4.3) to transcribe recorded audio files.  I have noticed that often the first few words of the transcript (output in notepad) tend to get missed out altogether or get messed up.  The quality of the rest of the transcript is excellent.  This happens even with a new profile.  I suspect (though I could be wrong) that the ATFA takes a few seconds to fully load one of the many profiles that I have created (based on different medical vocabularies) before it begins the transcription process.  Each user profile has a different input and output folder.
Is there a way I can delay (programmatically - by a few seconds) the start of the transcription process by the ATFA to give the user profile a chance to load fully?  The ATFA runs unattended and the audio input is taken from my dropbox folder.
Can a delay be added in the soptions.ini file or any other file?
 09/15/2021 04:18 PM
User is offline View Users Profile Print this message

Author Icon
R. Wilke
Top-Tier Member

Posts: 8116
Joined: 03/04/2007

A simple workaround might be starting the recording and then waiting a couple of seconds before starting to dictate. On a related note, whenever I transcribe audio files recorded "in the field", very often the first word(s) get missed in the transcription at the start of each utterance, whenever I switch the digital recorder from pausing to running; and most likely, I tend to start dictating too soon after the switch. This is also true for the "normal" transcription" mode, as that's the only one that I use, and I never use the Auto Transcribe Folder facility.


The New Game in Town: DragonConnect

32634 users are registered to the KnowBrainer Speech Recognition forum.
There are currently 0 users logged in.
The most users ever online was 12124 on 09/09/2020 at 04:59 AM.
There are currently 322 guests browsing this forum, which makes a total of 322 users using this forum.

FuseTalk Standard Edition v4.0 - © 1999-2023 FuseTalk™ Inc. All rights reserved.