HackerTrans
TopNewTrendsCommentsPastAskShowJobs

avibhu

no profile record

comments

avibhu
·2 jaar geleden·discuss
Ironic name.
avibhu
·2 jaar geleden·discuss
Have you tried few shot prompting? Something on the lines of:

User: Extract x from the given scanned document. <sample_img_1>

Assistant: <sample_img_1_output>

User: Extract x from the given scanned document. <sample_img_2>

Assistant: <sample_img_2_output>

User: Extract x from the given scanned document. <query_image>

In my experience, this seems to make the model significantly more consistent.
avibhu
·3 jaar geleden·discuss
For what its worth, very high quality OCR from Google's Vision offering costs $0.0015 per page, with 1000 free pages per month. In my experience, it has been signficantly superior to any open source solution.
avibhu
·3 jaar geleden·discuss
Can you share that string please?
avibhu
·3 jaar geleden·discuss
Tangential: you can finetune something like flan-ul2 to do quote extraction using examples generated from chatgpt. If you have a good enough GPU, it should help cut down costs significantly
avibhu
·3 jaar geleden·discuss
Not sure why there no direct replies to this, but 108 is a dedicated line for all emergencies. Interestingly 112 and 911 have also worked for me in the past when butt dialed.