Thank you for being a valued part of the CNET community. As of December 1, 2020, the forums are in read-only format. In early 2021, CNET Forums will no longer be available. We are grateful for the participation and advice you have provided to one another over the years.

Thanks,

CNET Support

Question

Speech to text

Jan 31, 2013 4:55PM PST

I am currently working as a captionist and am planning to make a transition to general transcribing.

Where I caption, we use voice recognition software while listening to audio. We use a pause pedal and correct errors as we go.

From what I understand, the speed requirement for transcribing is about 50 wpm (at least on job descriptions I've seen so far) I type 60 wpm. So, even with having to go back and make sure the spelling and grammar was perfect (not something I have to be concerned about at my current job; minor errors are ok and punctuation is not used)... wouldn't using a Voice Recognition software still be faster than just typing? Would transcription companies frown on that, or would they care?

Another question that came to my mind just now; where I work, we have to have a low error rate, our score has to be above 90%. (my average is 97%) What is the general acceptable error rate for transcribing?

I appreciate you taking time to read, and appreciate this forum. There's so much helpful info here!

Discussion is locked

- Collapse -
Answer
After years of OCR and more work.
Feb 4, 2013 12:50AM PST

The clients want no errors. Only after some discussion they will accept some errors such as color vs. colour but when financial numbers are at stake, the only accepted rate is 100% good. You can't accept errors when money is involved. That should be clear to you why.
Bob

- Collapse -
Answer
Auto?
Feb 12, 2013 7:24PM PST

Do you want a software or a service?

- Collapse -
My software can be a service.
Feb 13, 2013 12:23AM PST